Article(id=1322961427174129954, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322961355078246774, articleNumber=null, orderNo=null, doi=10.11834/jig.260210, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1776268800000, receivedDateStr=2026-04-16, revisedDate=1780588800000, revisedDateStr=2026-06-05, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348183672, onlineDateStr=2026-10-30, pubDate=1789488000000, pubDateStr=2026-09-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348183672, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348183672, creator=13701087609, updateTime=1793348183672, updator=13701087609, issue=Issue{id=1322961355078246774, tenantId=1146029695717560320, journalId=1249024232475115590, year='2026', volume='31', issue='9', pageStart='3075', pageEnd='3440', issueExtLink='null', onlineDate='null', pubDate='1789488000000', pubDateStr='2026-09-16', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793348166484, creator='13701087609', updateTime=1793348617535, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322963246994555810, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322961355078246774, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322963246998750115, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322961355078246774, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=3097, endPage=3119, ext={EN=ArticleExt(id=1322961427606143267, articleId=1322961427174129954, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=Intelligent processing of airborne spectral images: methods,applications,and challenges, columnId=1322961355891941751, journalTitle=Journal of Image and Graphics, columnName=The intelligent empowerment of large models in the aviation field, runingTitle=null, highlight=null, articleAbstract=

Airborne spectral imaging,including hyperspectral imaging (HSI) and multispectral imaging (MSI) data from unmanned aerial vehicles (UAVs) and manned aircraft,has become a cornerstone of modern remote sensing. Compared to satellites,airborne platforms offer ultra-high spatial resolution,operational flexibility,short revisit cycles,and customizable sensors. Because of these advantages,they have become indispensable for precision agriculture,environmental monitoring,military reconnaissance,urban planning,geological exploration,and cultural heritage preservation. However,airborne spectral data present unique challenges,including high dimensionality (especially for HSI with hundreds of bands),strong spectral-spatial correlations,complex noise,geometric distortions from platform motion,variable illumination,and the mixed-pixel problem. Traditional methods (e.g.,SVM,random forests,and physical models) struggle to fully exploit these data due to limited feature representation,the curse of dimensionality,and poor generalization across sensors or flight conditions. As such,this paper systematically reviews intelligent processing techniques for airborne spectral images,focusing on deep learning and advanced machine learning. First,we highlight the complementary roles of HSI and MSI,stating that HSI provides rich continuous spectra for fine material identification and sub-pixel analysis,while MSI offers higher signal-to-noise ratio,lower data volume,and better real-time performance. Their synergistic use,often in a layered strategy (MSI-based coarse detection followed by HSI-based fine identification),is a key trend. Next,we discuss in detail the preprocessing pipeline—radiometric calibration,atmospheric correction,geometric registration,denoising,and resolution enhancement—noting the shift from purely physical models to hybrid data-driven and physics-informed deep learning. The core of the review covers six intelligent processing tasks. For spectral-spatial feature extraction,we trace the evolution from 2D/3D CNNs and hybrid CNN-Transformer models to state-space models like Mamba,which have been shown to achieve linear complexity while capturing long-range spectral dependencies,balancing accuracy and efficiency for real-time scenarios. For classification and segmentation,we discuss supervised,semisupervised,few-shot,and self-supervised methods (e.g.,HybridSN,Spectral-Former,and masked spectral modeling),as well as lightweight networks (MobileNet and EfficientNet) and transfer learning dominate for MSI,with cross-domain few-shot learning addressing label scarcity. For target detection,HSI exploits subtle spectral differences for camouflaged targets and chemical agents using anomaly detection or Transformer-based detectors (e.g.,SpecDETR),while MSI leverages YOLO and Faster R-CNN for real-time object detection. In addition,multimodal fusion (visible,thermal,spectral) further improves robustness. For change detection (CD),Siamese networks,Transformers (BIT and ChangeFormer),and Mamba hybrids are applied to multitemporal images,overcoming specific challenges in distinguishing real changes from illumination/atmospheric variations and incorporating physical constraints. For spectral unmixing,autoencoders learn nonlinear mixtures but lack physical constraints (nonnegativity,sum-to-one,and energy conservation),with recent efforts embedding linear mixture or radiative transfer models into deep networks for better interpretability. For multisource fusion,we cover heterogeneous fusion (HIS + LiDAR and HIS + SAR) using multimodal Transformers or GNNs,as well as spectral-spectral fusion (HIS + MSI) to generate high-resolution hyperspectral data,outlining four collaborative strategies: HSI-guided band selection,MSI-assisted dimensionality reduction,layered cascaded processing,and end-to-end joint modeling. A dedicated section addresses real-time processing and lightweight deployment on airborne edge devices (e.g.,NVIDIA Jetson). Furthermore,we review model compression (pruning,quantization,knowledge distillation,and neural architecture search) and evaluate backbones (MobileNet,HybridSN,Mamba,and efficient Transformers) for onboard inference. While real-time HSI classification and MSI detection have been demonstrated,real-time unmixing and CD remain challenging. The paper surveys typical applications,emphasizing HSI/MSI complementarity,including precision agriculture (early disease detection,nutrient/water stress,and fruit counting),environmental and disaster monitoring (oil spills,red tides,forest fires,air pollution,and mining),military reconnaissance (camouflage target detection and chemical agents),urban and infrastructure (land cover classification,building CD,traffic,and infrastructure health),geological exploration (mineral mapping,alteration zones,and oil/gas microseepage),and archaeology (subsurface relics,surface disease analysis). Next,we identify five core challenges,namely scarcity of high-quality labeled data,insufficient model generalization,real-time constraints,and lack of interpretability (black-box models ignoring physical mechanisms),and difficulties in air-space-ground collaboration (heterogeneous data,limited bandwidth,and cross-platform transfer). Finally,we outline the following directions for future works: foundation models with self-supervised learning for spectral-spatial representation; lightweight edge intelligence via hardware-software co-design; physics-informed deep models embedding radiative transfer or mixture constraints; robust and trustworthy AI with adversarial defense and uncertainty quantification; and integrated air-space-ground collaborative observation systems for hierarchical and intelligent remote sensing. In summary,this review provides a systematic reference for researchers and engineers advancing airborne spectral image intelligent processing. The datasets mentioned in this paper have been compiled and are available at https://github.com/zhaoxb2025/Airb-spe-Img.

, authors=Xingbing Zhao1, Chenrui Guo2, 3, Yushan Li4, Lei Zhang5, *, Wei Wei5, authorsList=Xingbing Zhao, Chenrui Guo, Yushan Li, Lei Zhang, Wei Wei, authorCompany=null, correspAuthors=Lei Zhang, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322961451090051385, articleId=1322961427174129954, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=航空光谱图像智能处理:方法、应用与挑战, columnId=1322961356168765817, journalTitle=中国图象图形学报, columnName=大模型在航空领域的智慧赋能, runingTitle=null, highlight=null, articleAbstract=

随着无人机与机载遥感技术的快速发展,航空光谱成像在农业、环境监测及军事侦察等领域发挥着越来越重要的作用。相比卫星遥感,航空平台具有更高空间分辨率、更强机动性和更短重访周期,使其成为精细化观测的重要手段。然而,航空光谱数据具有高维、强相关和噪声复杂等特点,传统处理方法难以充分挖掘其潜在信息。本文系统梳理了航空光谱图像智能处理技术的发展脉络,重点分析深度学习与机器学习方法,涵盖光谱—空间特征提取、分类、分割、目标检测、变化检测及光谱解混等关键技术;总结多光谱与高光谱协同处理在精准农业、环境灾害监测、军事侦察以及地质勘探等场景的应用进展;深入剖析当前面临的数据稀缺与标注困难、模型泛化能力不足、实时处理约束、鲁棒性欠缺及空天地协同困难等核心挑战;围绕遥感基础模型、自监督学习、边缘智能、物理信息驱动模型以及空天地一体化协同等方向展望未来趋势。本文可为航空光谱图像智能处理领域的研究与工程应用提供系统性的参考与理论指导。本文提及的数据集已汇总至https://github.com/zhaoxb2025/Airb-spe-Img。

, authors=赵兴兵1, 郭宸瑞2, 3, 李羽珊4, 张磊5, *, 魏巍5, authorsList=赵兴兵, 郭宸瑞, 李羽珊, 张磊, 魏巍, authorCompany=null, correspAuthors=张磊, authorNote=

赵兴兵,男,博士研究生,主要研究方向为小样本高光谱图像分类。E-mail:

郭宸瑞,男,工程师,主要研究方向为目标检测和多模态大模型。E-mail:

李羽珊,女,硕士研究生,主要研究方向为目标检测和多模态图像融。E-mail:

张磊,通信作者,男,教授,主要研究方向为小样本学习、图像生成和主动学习。E-mail:

魏巍,男,教授,主要研究方向为遥感目标检测、变化检测和多模态图像融合。E-mail:

, correspAuthorsNote=
张磊
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=X2+AwfYU01wWJV6P+rbHzw==, magXml=kavhfe8oF/CcAmZ05eMT2w==, pdfUrl=null, pdf=bvZxtCg4AAdFqH5FOb/BOA==, pdfFileSize=15384374, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=p/nVYxURFThyvkNHULL1Ng==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=xy7Mj2R8BxMhoNYVSzdRoQ==, mapNumber=null, fund=null)}, authors=[Author(id=1322961454386774350, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xbzhao0@gmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961454458077520, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454386774350, language=EN, stringName=Xingbing Zhao, firstName=Xingbing, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National Elite Institute of Engineering,Northwestern Polytechnical University,Xi’an 710100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961454797816145, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454386774350, language=CN, stringName=赵兴兵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西北工业大学国家卓越工程师学院,西安 710100, bio={"content":"

赵兴兵,男,博士研究生,主要研究方向为小样本高光谱图像分类。E-mail:

"}, bioImg=null, bioContent=

赵兴兵,男,博士研究生,主要研究方向为小样本高光谱图像分类。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961452272845116, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=1, ext=[AuthorCompanyExt(id=1322961452281233725, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961452272845116, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Elite Institute of Engineering,Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961452318982462, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961452272845116, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学国家卓越工程师学院,西安 710100)])]), Author(id=1322961454894285139, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=g-ch-r@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961455141749079, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454894285139, language=EN, stringName=Chenrui Guo, firstName=Chenrui, middleName=null, lastName=Guo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 State Key Laboratory of Aerospace Intelligent Control Technology,Beijing 100854,China
3 Beijing Aerospace Automatic Control Institute, Beijing 100854,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961455221440856, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454894285139, language=CN, stringName=郭宸瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 宇航智能控制技术全国重点实验室,北京 100854
3 北京航天自动控制研究所,北京 100854, bio={"content":"

郭宸瑞,男,工程师,主要研究方向为目标检测和多模态大模型。E-mail:

"}, bioImg=null, bioContent=

郭宸瑞,男,工程师,主要研究方向为目标检测和多模态大模型。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453073957184, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=2, ext=[AuthorCompanyExt(id=1322961453090734401, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453073957184, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Key Laboratory of Aerospace Intelligent Control Technology,Beijing 100854,China), AuthorCompanyExt(id=1322961453111705922, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453073957184, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 宇航智能控制技术全国重点实验室,北京 100854)]), AuthorCompany(id=1322961453233340740, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=3, ext=[AuthorCompanyExt(id=1322961453455638853, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453233340740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Aerospace Automatic Control Institute, Beijing 100854,China), AuthorCompanyExt(id=1322961453518553414, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453233340740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京航天自动控制研究所,北京 100854)])]), Author(id=1322961455275966810, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=myssgxka@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961455561179484, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455275966810, language=EN, stringName=Yushan Li, firstName=Yushan, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 Qujing Health and Medical College,Qujing 655100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961455628288349, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455275966810, language=CN, stringName=李羽珊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 曲靖健康医学院,曲靖 655100, bio={"content":"

李羽珊,女,硕士研究生,主要研究方向为目标检测和多模态图像融。E-mail:

"}, bioImg=null, bioContent=

李羽珊,女,硕士研究生,主要研究方向为目标检测和多模态图像融。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453875069255, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=4, ext=[AuthorCompanyExt(id=1322961453879263560, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453875069255, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Qujing Health and Medical College,Qujing 655100,China), AuthorCompanyExt(id=1322961453891846473, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453875069255, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 曲靖健康医学院,曲靖 655100)])]), Author(id=1322961455691202911, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=nwpuzhanglei@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322961455762506081, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455691202911, language=EN, stringName=Lei Zhang, firstName=Lei, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961457503142242, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455691202911, language=CN, stringName=张磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 西北工业大学计算机学院,西安 710100, bio={"content":"

张磊,通信作者,男,教授,主要研究方向为小样本学习、图像生成和主动学习。E-mail:

"}, bioImg=null, bioContent=

张磊,通信作者,男,教授,主要研究方向为小样本学习、图像生成和主动学习。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453967343946, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=5, ext=[AuthorCompanyExt(id=1322961453988315467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961454302888268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学计算机学院,西安 710100)])]), Author(id=1322961457595416933, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=weiweinwpu@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961457687691623, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961457595416933, language=EN, stringName=Wei Wei, firstName=Wei, middleName=null, lastName=Wei, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961457758994792, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961457595416933, language=CN, stringName=魏巍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 西北工业大学计算机学院,西安 710100, bio={"content":"

魏巍,男,教授,主要研究方向为遥感目标检测、变化检测和多模态图像融合。E-mail:

"}, bioImg=null, bioContent=

魏巍,男,教授,主要研究方向为遥感目标检测、变化检测和多模态图像融合。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453967343946, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=5, ext=[AuthorCompanyExt(id=1322961453988315467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961454302888268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学计算机学院,西安 710100)])])], keywords=[Keyword(id=1322961457851269481, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=1, keyword=airborne spectral image), Keyword(id=1322961458073567594, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=2, keyword=hyperspectral image), Keyword(id=1322961458140676459, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=3, keyword=multispectral image), Keyword(id=1322961458203591020, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=4, keyword=intelligent processing), Keyword(id=1322961458266505581, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=5, keyword=object detection), Keyword(id=1322961458342003054, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=6, keyword=change detection), Keyword(id=1322961458409111919, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, orderNo=7, keyword=classification), Keyword(id=1322961458467832176, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=1, keyword=航空光谱图像), Keyword(id=1322961458547523953, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=2, keyword=高光谱图像), Keyword(id=1322961458610438514, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=3, keyword=多光谱图像), Keyword(id=1322961458690130291, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=4, keyword=智能处理), Keyword(id=1322961458761433460, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=5, keyword=目标检测), Keyword(id=1322961458849513845, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=6, keyword=变化检测), Keyword(id=1322961458912428406, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, orderNo=7, keyword=分类)], refs=[Reference(id=1322961463203201425, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2018, volume=10, issue=7, pageStart=null, pageEnd=1091, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Aasen H, Honkavaara E, Lucieer A, Zarco-Tejada P J, journalName=Remote Sensing, refType=null, unstructuredReference=Aasen H,Honkavaara E,Lucieer A and Zarco-Tejada P J. 2018. Quantitative remote sensing at ultra-high resolution with UAV spectroscopy: a review of sensor technology,measurement procedures,and data correction workflows. Remote Sensing,10(7): #1091 [DOI: 10.3390/rs10071091], articleTitle=Quantitative remote sensing at ultra-high resolution with UAV spectroscopy: a review of sensor technology,measurement procedures,and data correction workflows, refAbstract=null), Reference(id=1322961463261921682, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=4, issue=3, pageStart=null, pageEnd=46, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Adamopoulos E, Rinaudo F, journalName=Drones, refType=null, unstructuredReference=Adamopoulos E and Rinaudo F. 2020. UAS-based archaeological remote sensing: review,meta-analysis and state-of-the-art. Drones,4(3): #46 [DOI: 10.3390/drones4030046], articleTitle=UAS-based archaeological remote sensing: review,meta-analysis and state-of-the-art, refAbstract=null), Reference(id=1322961463337419155, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=9, issue=11, pageStart=null, pageEnd=1110, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Adão T, Hruška J, P􀅡dua L, Bessa J, Peres E, Morais R, journalName=Remote Sensing, refType=null, unstructuredReference=Adão T,Hruška J,P􀅡dua L,Bessa J,Peres E,Morais R,et al. 2017. Hyperspectral imaging: a review on UAV-based sensors,data processing and applications for agriculture and forestry. Remote Sensing,9(11): #1110 [DOI: 10.3390/rs9111110], articleTitle=Hyperspectral imaging: a review on UAV-based sensors,data processing and applications for agriculture and forestry, refAbstract=null), Reference(id=1322961463412916628, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=16, issue=4, pageStart=339, pageEnd=353, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Ahmad M, Butt M H F, Usama M, Altuwaijri H A, Mazzara M, Distefano S, journalName=Remote Sensing Letters, refType=null, unstructuredReference=Ahmad M,Butt M H F,Usama M,Altuwaijri H A,Mazzara M,Distefano S,et al. 2025. Multi-head spatial-spectral mamba for hyperspectral image classification. Remote Sensing Letters,16(4): 339-353 [DOI: 10.1080/2150704X.2025.2461330], articleTitle=Multi-head spatial-spectral mamba for hyperspectral image classification, refAbstract=null), Reference(id=1322961463480025494, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=25, issue=8, pageStart=null, pageEnd=2592, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Alshahrani A A, Bchir O, Ben Ismail M M, journalName=Sensors, refType=null, unstructuredReference=Alshahrani A A,Bchir O and Ben Ismail M M. 2025. Autoencoder-based hyperspectral unmixing with simultaneous number-of-endmembers estimation. Sensors,25(8): #2592 [DOI: 10.3390/s25082592], articleTitle=Autoencoder-based hyperspectral unmixing with simultaneous number-of-endmembers estimation, refAbstract=null), Reference(id=1322961463551328663, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=11, issue=4, pageStart=null, pageEnd=042609, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Ball J E, Anderson D T, Chan C S, journalName=Journal of Applied Remote Sensing, refType=null, unstructuredReference=Ball J E,Anderson D T and Chan C S. 2017. Comprehensive survey of deep learning in remote sensing: theories,tools,and challenges for the community. Journal of Applied Remote Sensing,11(4): #042609 [DOI: 10.1117/1.jrs.11.042609], articleTitle=Comprehensive survey of deep learning in remote sensing: theories,tools,and challenges for the community, refAbstract=null), Reference(id=1322961463635214744, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=207, pageEnd=210, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=Bandara W G C, Patel V M, journalName=2022 IGARSS IEEE International Geoscience and Remote Sensing Symposium, refType=null, unstructuredReference=Bandara W G C and Patel V M. 2022. A transformer-based Siamese network for change detection//2022 IGARSS IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur,Malaysia: IEEE: 207-210 [DOI: 10.1109/IGARSS46834.2022.9883686], articleTitle=A transformer-based Siamese network for change detection, refAbstract=null), Reference(id=1322961463714906521, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2011, volume=47, issue=1, pageStart=60, pageEnd=73, url=null, language=null, rfNumber=null, rfOrder=7, authorNames=Bedini E, journalName=Advances in Space Research, refType=null, unstructuredReference=Bedini E. 2011. Mineral mapping in the Kap Simpson complex,central East Greenland,using HyMap and ASTER remote sensing data. Advances in Space Research,47(1): 60-73 [DOI: 10.1016/j.asr.2010.08.021], articleTitle=Mineral mapping in the Kap Simpson complex,central East Greenland,using HyMap and ASTER remote sensing data, refAbstract=null), Reference(id=1322961463790403994, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2012, volume=5, issue=2, pageStart=354, pageEnd=379, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Bioucas-Dias J M, Plaza A, Dobigeon N, Parente M, Du Q, Gader P, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Bioucas-Dias J M,Plaza A,Dobigeon N,Parente M,Du Q,Gader P,et al. 2012. Hyperspectral unmixing overview: geometrical,statistical,and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,5(2): 354-379 [DOI: 10.1109/JSTARS.2012.2194696], articleTitle=Hyperspectral unmixing overview: geometrical,statistical,and sparse regression-based approaches, refAbstract=null), Reference(id=1322961463937204635, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=18, issue=null, pageStart=16780, pageEnd=16797, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Braham N A A, Albrecht C M, Mairal J, Chanussot J, Wang Y, Zhu X X, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Braham N A A,Albrecht C M,Mairal J,Chanussot J,Wang Y and Zhu X X. 2025. SpectralEarth: training hyperspectral foundation models at scale. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,18: 16780-16797 [DOI: 10.1109/JSTARS.2025.3581451], articleTitle=SpectralEarth: training hyperspectral foundation models at scale, refAbstract=null), Reference(id=1322961464008507804, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=1, pageStart=45, pageEnd=54, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Camps-Valls G, Tuia D, Bruzzone L, Benediktsson J A, journalName=IEEE Signal Processing Magazine, refType=null, unstructuredReference=Camps-Valls G,Tuia D,Bruzzone L and Benediktsson J A. 2014. Advances in hyperspectral image classification: earth monitoring with statistical learning methods. IEEE Signal Processing Magazine,31(1): 45-54 [DOI: 10.1109/msp.2013.2279179], articleTitle=Advances in hyperspectral image classification: earth monitoring with statistical learning methods, refAbstract=null), Reference(id=1322961464079810973, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=12, issue=3, pageStart=973, pageEnd=988, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=Cao C H, Yu J, Zhou C Y, Hu K, Xiao F, Gao X P, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Cao C H,Yu J,Zhou C Y,Hu K,Xiao F and Gao X P. 2019. Hyperspectral image denoising via subspace-based nonlocal low-rank and sparse factorization. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,12(3): 973-988 [DOI: 10.1109/JSTARS.2019.2896031], articleTitle=Hyperspectral image denoising via subspace-based nonlocal low-rank and sparse factorization, refAbstract=null), Reference(id=1322961464180474270, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=13, issue=5, pageStart=null, pageEnd=364, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Cao S H, Wang T, Li T, Fei S M, journalName=Machines, refType=null, unstructuredReference=Cao S H,Wang T,Li T and Fei S M. 2025. UAV real-time target detection and tracking algorithm based on improved KCF and YOLOv5s_MSES. Machines,13(5): #364 [DOI: 10.3390/machines13050364], articleTitle=UAV real-time target detection and tracking algorithm based on improved KCF and YOLOv5s_MSES, refAbstract=null), Reference(id=1322961464251777439, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2509.13229.pdf, language=null, rfNumber=null, rfOrder=13, authorNames=Carlesso H, Mothe J, Ionescu R T, journalName=null, refType=null, unstructuredReference=Carlesso H,Mothe J and Ionescu R T. 2025. Curriculum multi-task self-supervision improves lightweight architectures for onboard satellite hyperspectral image segmentation [EB/OL]. [2026-04-01]., articleTitle=Curriculum multi-task self-supervision improves lightweight architectures for onboard satellite hyperspectral image segmentation, refAbstract=null), Reference(id=1322961464369217952, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=82, issue=null, pageStart=null, pageEnd=102615, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Chen J Y, Frey E C, He Y F, Segars W P, Li Y, Du Y, journalName=Medical Image Analysis, refType=null, unstructuredReference=Chen J Y,Frey E C,He Y F,Segars W P,Li Y and Du Y. 2022. TransMorph: transformer for unsupervised medical image registration. Medical Image Analysis,82: #102615 [DOI: 10.1016/j.media.2022.102615], articleTitle=TransMorph: transformer for unsupervised medical image registration, refAbstract=null), Reference(id=1322961464440521121, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1597, pageEnd=1607, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Chen T, Kornblith S, Norouzi M, Hinton G E, journalName=null, refType=null, unstructuredReference=Chen T,Kornblith S,Norouzi M and Hinton G E. 2020. A simple framework for contrastive learning of visual representations//Proceedings of the 37th International Conference on Machine Learning. [s.l.]: PMLR: 1597-1607, articleTitle=A simple framework for contrastive learning of visual representations, refAbstract=null), Reference(id=1322961464528601506, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2016, volume=54, issue=10, pageStart=6232, pageEnd=6251, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=Chen Y, Jiang H, Li C, Jia X, Ghamisi P, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Chen Y,Jiang H,Li C,Jia X and Ghamisi P. 2016. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing,54(10): 6232-6251 [DOI: 10.1109/TGRS.2016.2584107], articleTitle=Deep feature extraction and classification of hyperspectral images based on convolutional neural networks, refAbstract=null), Reference(id=1322961464608293283, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=14, issue=18, pageStart=null, pageEnd=4523, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Chi Q, Lyu G H, Zhao G X, Dong X J, journalName=Remote Sensing, refType=null, unstructuredReference=Chi Q,Lyu G H,Zhao G X and Dong X J. 2022. A novel knowledge distillation method for self-supervised hyperspectral image classification. Remote Sensing,14(18): #4523 [DOI: 10.3390/rs14184523], articleTitle=A novel knowledge distillation method for self-supervised hyperspectral image classification, refAbstract=null), Reference(id=1322961464801231268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=11, pageStart=null, pageEnd=2909, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Daniels L, Eeckhout E, Wieme J, Dejaegher Y, Audenaert K, Maes W H, journalName=Remote Sensing, refType=null, unstructuredReference=Daniels L,Eeckhout E,Wieme J,Dejaegher Y,Audenaert K and Maes W H. 2023. Identifying the optimal radiometric calibration method for UAV-based multispectral imaging. Remote Sensing,15(11): #2909 [DOI: 10.3390/rs15112909], articleTitle=Identifying the optimal radiometric calibration method for UAV-based multispectral imaging, refAbstract=null), Reference(id=1322961466474758565, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2018, volume=10, issue=8, pageStart=null, pageEnd=1216, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=Dash J P, Pearse G D, Watt M S, journalName=Remote Sensing, refType=null, unstructuredReference=Dash J P,Pearse G D and Watt M S. 2018. UAV multispectral imagery can complement satellite data for monitoring forest health. Remote Sensing,10(8): #1216 [DOI: 10.3390/rs10081216], articleTitle=UAV multispectral imagery can complement satellite data for monitoring forest health, refAbstract=null), Reference(id=1322961466546061734, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=4063, pageEnd=4067, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Daudt R C, Le Saux B, Boulch A, journalName=null, refType=null, unstructuredReference=Daudt R C,Le Saux B and Boulch A. 2018. Fully convolutional Siamese networks for change detection//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens,Greece: IEEE: 4063-4067 [DOI: 10.1109/ICIP.2018.8451652], articleTitle=Fully convolutional Siamese networks for change detection, refAbstract=null), Reference(id=1322961466894188967, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=6, pageStart=1714, pageEnd=1729, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Ding C, Chen J Y, Zheng M M, Zhang L, Wei W, Zhang Y N, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Ding C,Chen J Y,Zheng M M,Zhang L,Wei W and Zhang Y N. 2024. Survey of hyperspectral image change detection method. Journal of Image and Graphics,29(6): 1714-1729, articleTitle=Survey of hyperspectral image change detection method, refAbstract=null), Reference(id=1322961466965492136, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=6, pageStart=1714, pageEnd=1729, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=丁晨, 陈静怡, 郑萌萌, 张磊, 魏巍, 张艳宁, journalName=中国图象图形学报, refType=null, unstructuredReference=丁晨,陈静怡,郑萌萌,张磊,魏巍,张艳宁. 2024. 高光谱图像变化检测技术研究进展. 中国图象图形学报,29(6): 1714-1729 [DOI: 10.11834/jig.240031], articleTitle=高光谱图像变化检测技术研究进展, refAbstract=null), Reference(id=1322961467036795305, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=1, pageStart=82, pageEnd=94, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=Dobigeon N, Tourneret J Y, Richard C, Bermudez J C M, McLaughlin S, Hero A O, journalName=IEEE Signal Processing Magazine, refType=null, unstructuredReference=Dobigeon N,Tourneret J Y,Richard C,Bermudez J C M,McLaughlin S and Hero A O. 2014. Nonlinear unmixing of hyperspectral images: models and algorithms. IEEE Signal Processing Magazine,31(1): 82-94 [DOI: 10.1109/MSP.2013.2279274], articleTitle=Nonlinear unmixing of hyperspectral images: models and algorithms, refAbstract=null), Reference(id=1322961467301036458, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=63, issue=null, pageStart=null, pageEnd=112128, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Doornbos J and Babur Ö, journalName=Data in Brief, refType=null, unstructuredReference=Doornbos J and Babur Ö. 2025. msuav500k: foundational dataset for multispectral and RGB uncrewed aerial vehicle imagery. Data in Brief,63: #112128 [DOI: 10.1016/j.dib.2025.112128], articleTitle=msuav500k: foundational dataset for multispectral and RGB uncrewed aerial vehicle imagery, refAbstract=null), Reference(id=1322961467368145323, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=4, pageStart=#0404002, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Duan W M, Xiong Y H, Chen Z W, Yu G B, Liu L M, Li F Q, journalName=Acta Photonica Sinica, refType=null, unstructuredReference=Duan W M,Xiong Y H,Chen Z W,Yu G B,Liu L M,Li F Q,et al. 2020. Remote sensing and monitoring of industrial SO2 and carbon black particles with ultraviolet imaging technology. Acta Photonica Sinica,49(4): #0404002, articleTitle=Remote sensing and monitoring of industrial SO2 and carbon black particles with ultraviolet imaging technology, refAbstract=null), Reference(id=1322961467443642796, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=4, pageStart=#0404002, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=段为民, 熊远辉, 陈振威, 于光保, 刘林美, 李发泉, journalName=光子学报, refType=null, unstructuredReference=段为民,熊远辉,陈振威,于光保,刘林美,李发泉,等. 2020. 工业SO2及碳黑颗粒紫外成像遥感监测技术. 光子学报,49(4): #0404002 [DOI: 10.3788/gzxb20204904.0404002], articleTitle=工业SO2及碳黑颗粒紫外成像遥感监测技术, refAbstract=null), Reference(id=1322961467783381421, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=6, pageStart=1151, pageEnd=1158, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=El Zaar A, Assawab R, Aoulalay A, Benaya N, Bakir T, Femmam S, journalName=Journal of Advances in Information Technology, refType=null, unstructuredReference=El Zaar A,Assawab R,Aoulalay A,Benaya N,Bakir T,Femmam S,et al. 2023. MFTs-Net: a deep learning approach for high similarity date fruit recognition. Journal of Advances in Information Technology,14(6): 1151-1158 [DOI: 10.12720/jait.14.6.1151-1158], articleTitle=MFTs-Net: a deep learning approach for high similarity date fruit recognition, refAbstract=null), Reference(id=1322961468148285870, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=1997, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=Fingas M F, Brown C E, journalName=null, refType=null, unstructuredReference=Fingas M F and Brown C E. 1997. Oil spill remote sensors: review,trends and new developments. CONF-970319. [s.n.], articleTitle=Oil spill remote sensors: review,trends and new developments. CONF-970319, refAbstract=null), Reference(id=1322961468236366255, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=#59761, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=29, authorNames=Franke J, Menz G, Oerke E C, Rascher U, journalName=Proceedings of SPIE 5976,Remote Sensing for Agriculture,Ecosystems,and Hydrology VII, refType=null, unstructuredReference=Franke J,Menz G,Oerke E C and Rascher U. 2005. Comparison of multi- and hyperspectral imaging data of leaf rust infected wheat plants//Proceedings of SPIE 5976,Remote Sensing for Agriculture,Ecosystems,and Hydrology VII. Bruges,Belgium: SPIE: #59761D [DOI: 10.1117/12.626531], articleTitle=Comparison of multi- and hyperspectral imaging data of leaf rust infected wheat plants, refAbstract=null), Reference(id=1322961468559327664, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=5, issue=4, pageStart=37, pageEnd=78, url=null, language=null, rfNumber=null, rfOrder=30, authorNames=Ghamisi P, Yokoya N, Li J, Liao W Z, Liu S C, Plaza J, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Ghamisi P,Yokoya N,Li J,Liao W Z,Liu S C,Plaza J,et al. 2017. Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art. IEEE Geoscience and Remote Sensing Magazine,5(4): 37-78 [DOI: 10.1109/mgrs.2017.2762087], articleTitle=Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art, refAbstract=null), Reference(id=1322961468626436529, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=null, rfOrder=31, authorNames=Gladkikh T Y, Rusakov K D, Grafenkov A V, journalName=null, refType=null, unstructuredReference=Gladkikh T Y,Rusakov K D and Grafenkov A V. 2024. Oil pollution detection in aquatic ecosystems using UAVs and multispectral imaging based on deep learning technologies//Proceedings of the 8th International Conference on Information,Control,and Communication Technologies (ICCT). Vladikavkaz,Russian Federation: IEEE: 1-5 [DOI: 10.1109/ICCT62929.2024.10874968], articleTitle=Oil pollution detection in aquatic ecosystems using UAVs and multispectral imaging based on deep learning technologies, refAbstract=null), Reference(id=1322961468693545394, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2312.00752.pdf, language=null, rfNumber=null, rfOrder=32, authorNames=Gu A, Dao T, journalName=null, refType=null, unstructuredReference=Gu A and Dao T. 2024. Mamba: linear-time sequence modeling with selective state spaces [EB/OL]. [2026-04-01]., articleTitle=Mamba: linear-time sequence modeling with selective state spaces, refAbstract=null), Reference(id=1322961468760654260, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=35, issue=null, pageStart=null, pageEnd=101218, url=null, language=null, rfNumber=null, rfOrder=33, authorNames=Hajaj S, El Harti A, Pour A B, Jellouli A, Adiri Z, Hashim M, journalName=Remote Sensing Applications: Society and Environment, refType=null, unstructuredReference=Hajaj S,El Harti A,Pour A B,Jellouli A,Adiri Z and Hashim M. 2024. A review on hyperspectral imagery application for lithological mapping and mineral prospecting: machine learning techniques and future prospects. Remote Sensing Applications: Society and Environment,35: #101218 [DOI: 10.1016/j.rsase.2024.101218], articleTitle=A review on hyperspectral imagery application for lithological mapping and mineral prospecting: machine learning techniques and future prospects, refAbstract=null), Reference(id=1322961468978758069, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=15979, pageEnd=15988, url=null, language=null, rfNumber=null, rfOrder=34, authorNames=He K M, Chen X L, Xie S N, Li Y H, Doll􀅡r P and Girshick R, journalName=null, refType=null, unstructuredReference=He K M,Chen X L,Xie S N,Li Y H,Doll􀅡r P and Girshick R. 2022. Masked autoencoders are scalable vision learners//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans,USA: IEEE: 15979-15988 [DOI: 10.1109/CVPR52688.2022.01553], articleTitle=Masked autoencoders are scalable vision learners, refAbstract=null), Reference(id=1322961469092004278, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=16, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=35, authorNames=He M Y, He J R, Liu H C, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=He M Y,He J R and Liu H C. 2026. Diversity prompt-guided cross-domain few-shot learning for hyperspectral image classification[J/OL]. Journal of Image and Graphics,1-16, articleTitle=Diversity prompt-guided cross-domain few-shot learning for hyperspectral image classification, refAbstract=null), Reference(id=1322961469393994167, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=16, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=36, authorNames=何梦瑶, 何进荣, 刘寒池, journalName=中国图象图形学报, refType=null, unstructuredReference=何梦瑶,何进荣,刘寒池. 2026. 多样性提示引导的跨域小样本高光谱图像分类[J/OL]. 中国图象图形学报,1-16 [DOI: 10.11834/jig.250585], articleTitle=多样性提示引导的跨域小样本高光谱图像分类, refAbstract=null), Reference(id=1322961471092687288, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/1503.02531.pdf, language=null, rfNumber=null, rfOrder=37, authorNames=Hinton G, Vinyals O, Dean J, journalName=null, refType=null, unstructuredReference=Hinton G,Vinyals O and Dean J. 2015. Distilling the knowledge in a neural network [EB/OL]. [2026-04-01]., articleTitle=Distilling the knowledge in a neural network, refAbstract=null), Reference(id=1322961471180767673, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=null, pageEnd=5518615, url=null, language=null, rfNumber=null, rfOrder=38, authorNames=Hong D F, Han Z, Yao J, Gao L R, Zhang B, Plaza A, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Hong D F,Han Z,Yao J,Gao L R,Zhang B,Plaza A,et al. 2022. SpectralFormer: rethinking hyperspectral image classification with transformers. IEEE Transactions on Geoscience and Remote Sensing,60: #5518615 [DOI: 10.1109/tgrs.2021.3130716], articleTitle=SpectralFormer: rethinking hyperspectral image classification with transformers, refAbstract=null), Reference(id=1322961471491146170, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=2017, pageEnd=2025, url=null, language=null, rfNumber=null, rfOrder=39, authorNames=Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K, journalName=null, refType=null, unstructuredReference=Jaderberg M,Simonyan K,Zisserman A and Kavukcuoglu K. 2015. Spatial transformer networks//Proceedings of the 29th International Conference on Neural Information Processing Systems. Montreal,Canada: MIT Press: 2017-2025, articleTitle=Spatial transformer networks, refAbstract=null), Reference(id=1322961471579226555, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=138, issue=null, pageStart=null, pageEnd=104457, url=null, language=null, rfNumber=null, rfOrder=40, authorNames=Ji R J, Tan K, Wang X, Tang S W, Sun J, Niu C, journalName=International Journal of Applied Earth Observation and Geoinformation, refType=null, unstructuredReference=Ji R J,Tan K,Wang X,Tang S W,Sun J,Niu C,et al. 2025. PatchOut: a novel patch-free approach based on a transformer-CNN hybrid framework for fine-grained land-cover classification on large-scale airborne hyperspectral images. International Journal of Applied Earth Observation and Geoinformation,138: #104457 [DOI: 10.1016/j.jag.2025.104457], articleTitle=PatchOut: a novel patch-free approach based on a transformer-CNN hybrid framework for fine-grained land-cover classification on large-scale airborne hyperspectral images, refAbstract=null), Reference(id=1322961471700861372, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=16, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=41, authorNames=Ji Y R, Wang C H, Chen J B, Yue A Z, Xi Z H, Chen J S, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Ji Y R,Wang C H,Chen J B,Yue A Z,Xi Z H and Chen J S. 2026. Parameter-efficient diffusion model adaptation and spectral consistency learning for controllable multispectral remote sensing image generation[J/OL]. Journal of Image and Graphics,1-16, articleTitle=Parameter-efficient diffusion model adaptation and spectral consistency learning for controllable multispectral remote sensing image generation, refAbstract=null), Reference(id=1322961471998656957, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=16, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=42, authorNames=纪璎芮, 王晨昊, 陈静波, 岳安志, 席智浩, 陈建胜, journalName=中国图象图形学报, refType=null, unstructuredReference=纪璎芮,王晨昊,陈静波,岳安志,席智浩,陈建胜. 2026. 多光谱遥感图像可控生成的扩散模型参数高效适配与光谱一致性学习[J/OL]. 中国图象图形学报,1-16 [DOI: 10.11834/jig.260089], articleTitle=多光谱遥感图像可控生成的扩散模型参数高效适配与光谱一致性学习, refAbstract=null), Reference(id=1322961472350978494, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=11, pageStart=4037, pageEnd=4058, url=null, language=null, rfNumber=null, rfOrder=43, authorNames=Jing L L, Tian Y L, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Jing L L and Tian Y L. 2021. Self-supervised visual feature learning with deep neural networks: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence,43(11): 4037-4058 [DOI: 10.1109/tpami.2020.2992393], articleTitle=Self-supervised visual feature learning with deep neural networks: a survey, refAbstract=null), Reference(id=1322961472430670271, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=null, rfOrder=44, authorNames=Justo J A, Garrett J, Langer D D, Henriksen M B, Ionescu R T, Johansen T A, journalName=2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), refType=null, unstructuredReference=Justo J A,Garrett J,Langer D D,Henriksen M B,Ionescu R T and Johansen T A. 2023. An open hyperspectral dataset with sea-land-cloud ground-truth from the Hypso-1 satellite//2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). Athens,Greece: IEEE: 1-5 [DOI: 10.1109/WHISPERS61460.2023.10431177], articleTitle=An open hyperspectral dataset with sea-land-cloud ground-truth from the Hypso-1 satellite, refAbstract=null), Reference(id=1322961472762020288, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2507.22650.pdf, language=null, rfNumber=null, rfOrder=45, authorNames=Kabir S, Rifti I A, Tabib H M S, Rahman M, Sadi S I, Adil H, journalName=null, refType=null, unstructuredReference=Kabir S,Rifti I A,Tabib H M S,Rahman M,Sadi S I,Adil H,et al. 2025. SpectraSentinel: LightWeight dual-stream real-time drone detection,tracking and payload identification [EB/OL]. [2026-04-01]., articleTitle=SpectraSentinel: LightWeight dual-stream real-time drone detection,tracking and payload identification, refAbstract=null), Reference(id=1322961472866877889, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2003, volume=41, issue=6, pageStart=1388, pageEnd=1400, url=null, language=null, rfNumber=null, rfOrder=46, authorNames=Kruse F A, Boardman J W, Huntington J F, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Kruse F A,Boardman J W and Huntington J F. 2003. Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping. IEEE Transactions on Geoscience and Remote Sensing,41(6): 1388-1400 [DOI: 10.1109/TGRS.2003.812908], articleTitle=Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping, refAbstract=null), Reference(id=1322961473231782338, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=105, pageEnd=114, url=null, language=null, rfNumber=null, rfOrder=47, authorNames=Ledig C, Theis L, Husz􀅡r F, Caballero J, Cunningham A, Acosta A, journalName=null, refType=null, unstructuredReference=Ledig C,Theis L,Husz􀅡r F,Caballero J,Cunningham A,Acosta A,et al. 2017. Photo-realistic single image super-resolution using a generative adversarial network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,USA: IEEE: 105-114 [DOI: 10.1109/CVPR.2017.19], articleTitle=Photo-realistic single image super-resolution using a generative adversarial network, refAbstract=null), Reference(id=1322961473324057027, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2510.02700.pdf, language=null, rfNumber=null, rfOrder=48, authorNames=Lekhak S, Ientilucci E J, Baur J, Ghosh S, journalName=null, refType=null, unstructuredReference=Lekhak S,Ientilucci E J,Baur J and Ghosh S. 2026. A UAV-based VNIR hyperspectral benchmark dataset for landmine and UXO detection [EB/OL]. [2026-04-01]., articleTitle=A UAV-based VNIR hyperspectral benchmark dataset for landmine and UXO detection, refAbstract=null), Reference(id=1322961473600881092, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=64, issue=null, pageStart=null, pageEnd=5501016, url=null, language=null, rfNumber=null, rfOrder=49, authorNames=Li D K, Bhatti U A, Huang M X, Bruzzone L, Li J X, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Li D K,Bhatti U A,Huang M X,Bruzzone L and Li J X. 2026. HyPyraMamba: a pyramid spectral attention and mamba-based architecture for robust hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,64: #5501016 [DOI: 10.1109/tgrs.2025.3650350], articleTitle=HyPyraMamba: a pyramid spectral attention and mamba-based architecture for robust hyperspectral image classification, refAbstract=null), Reference(id=1322961475278602693, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2507.04409.pdf, language=null, rfNumber=null, rfOrder=50, authorNames=Li G D, Ye M X, journalName=null, refType=null, unstructuredReference=Li G D and Ye M X. 2025. MVNet: hyperspectral remote sensing image classification based on hybrid mamba-transformer vision backbone architecture [EB/OL]. [2026-04-01]., articleTitle=MVNet: hyperspectral remote sensing image classification based on hybrid mamba-transformer vision backbone architecture, refAbstract=null), Reference(id=1322961475706421702, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=9, issue=1, pageStart=null, pageEnd=67, url=null, language=null, rfNumber=null, rfOrder=51, authorNames=Li Y, Zhang H K, Shen Q, journalName=Remote Sensing, refType=null, unstructuredReference=Li Y,Zhang H K and Shen Q. 2017. Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sensing,9(1): #67 [DOI: 10.3390/rs9010067], articleTitle=Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network, refAbstract=null), Reference(id=1322961475807084999, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025b, volume=226, issue=null, pageStart=221, pageEnd=246, url=null, language=null, rfNumber=null, rfOrder=52, authorNames=Li Z X, An W, Guo G W, Wang L G, Wang Y Q, Lin Z P, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference=Li Z X,An W,Guo G W,Wang L G,Wang Y Q and Lin Z P. 2025b. SpecDETR: a transformer-based hyperspectral point object detection network. ISPRS Journal of Photogrammetry and Remote Sensing,226: 221-246 [DOI: 10.1016/j.isprsjprs.2025.05.005], articleTitle=SpecDETR: a transformer-based hyperspectral point object detection network, refAbstract=null), Reference(id=1322961476163600840, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=57, issue=4, pageStart=2290, pageEnd=2304, url=null, language=null, rfNumber=null, rfOrder=53, authorNames=Liu B, Yu X C, Yu A Z, Zhang P Q, Wan G, Wang R R, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Liu B,Yu X C,Yu A Z,Zhang P Q,Wan G and Wang R R. 2019. Deep few-shot learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,57(4): 2290-2304 [DOI: 10.1109/TGRS.2018.2872830], articleTitle=Deep few-shot learning for hyperspectral image classification, refAbstract=null), Reference(id=1322961476532699594, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=8, issue=9, pageStart=839, pageEnd=848, url=null, language=null, rfNumber=null, rfOrder=54, authorNames=Liu B, Yu X C, Zhang P Q, Tan X, Yu A Z, Xue Z X, journalName=Remote Sensing Letters, refType=null, unstructuredReference=Liu B,Yu X C,Zhang P Q,Tan X,Yu A Z and Xue Z X. 2017. A semi-supervised convolutional neural network for hyperspectral image classification. Remote Sensing Letters,8(9): 839-848 [DOI: 10.1080/2150704X.2017.1331053], articleTitle=A semi-supervised convolutional neural network for hyperspectral image classification, refAbstract=null), Reference(id=1322961476608197067, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025a, volume=63, issue=null, pageStart=null, pageEnd=5511014, url=null, language=null, rfNumber=null, rfOrder=55, authorNames=Liu P F, Bai H Y, Xu T F, Wang J H, Chen H, Li J N, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Liu P F,Bai H Y,Xu T F,Wang J H,Chen H and Li J N. 2025a. Hyperspectral remote sensing images salient object detection: the first benchmark dataset and baseline. IEEE Transactions on Geoscience and Remote Sensing,63: #5511014 [DOI: 10.1109/TGRS.2025.3558189], articleTitle=Hyperspectral remote sensing images salient object detection: the first benchmark dataset and baseline, refAbstract=null), Reference(id=1322961476947935692, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025b, volume=231, issue=null, pageStart=null, pageEnd=110007, url=null, language=null, rfNumber=null, rfOrder=56, authorNames=Liu T, Qi Y, Yang F, Yi X Y, Guo S L, Wu P Y, journalName=Computers and Electronics in Agriculture, refType=null, unstructuredReference=Liu T,Qi Y,Yang F,Yi X Y,Guo S L,Wu P Y,et al. 2025b. Early detection of rice blast using UAV hyperspectral imagery and multi-scale integrator selection attention transformer network (MS-STNet). Computers and Electronics in Agriculture,231: #110007 [DOI: 10.1016/j.compag.2025.110007], articleTitle=Early detection of rice blast using UAV hyperspectral imagery and multi-scale integrator selection attention transformer network (MS-STNet), refAbstract=null), Reference(id=1322961477036016077, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2021, volume=18, issue=5, pageStart=811, pageEnd=815, url=null, language=null, rfNumber=null, rfOrder=57, authorNames=Liu Y, Pang C, Zhan Z Q, Zhang X M, Yang X, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Liu Y,Pang C,Zhan Z Q,Zhang X M and Yang X. 2021. Building change detection for remote sensing images using a dual-task constrained deep Siamese convolutional network model. IEEE Geoscience and Remote Sensing Letters,18(5): 811-815 [DOI: 10.1109/LGRS.2020.2988032], articleTitle=Building change detection for remote sensing images using a dual-task constrained deep Siamese convolutional network model, refAbstract=null), Reference(id=1322961477103124942, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025c, volume=17, issue=11, pageStart=null, pageEnd=1864, url=null, language=null, rfNumber=null, rfOrder=58, authorNames=Liu Y, Zhang Y J, Zhang J H, journalName=Remote Sensing, refType=null, unstructuredReference=Liu Y,Zhang Y J and Zhang J H. 2025c. Lightweight multi-head MambaOut with CosTaylorFormer for hyperspectral image classification. Remote Sensing,17(11): #1864 [DOI: 10.3390/rs17111864], articleTitle=Lightweight multi-head MambaOut with CosTaylorFormer for hyperspectral image classification, refAbstract=null), Reference(id=1322961477367366096, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2015, volume=3, issue=3, pageStart=27, pageEnd=46, url=null, language=null, rfNumber=null, rfOrder=59, authorNames=Loncan L, de Almeida L B, Bioucas-Dias J M, Briottet X, Chanussot J, Dobigeon N, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Loncan L,de Almeida L B,Bioucas-Dias J M,Briottet X,Chanussot J,Dobigeon N,et al. 2015. Hyperspectral pansharpening: a review. IEEE Geoscience and Remote Sensing Magazine,3(3): 27-46 [DOI: 10.1109/MGRS.2015.2440094], articleTitle=Hyperspectral pansharpening: a review, refAbstract=null), Reference(id=1322961477442863569, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=5, pageStart=null, pageEnd=1041, url=null, language=null, rfNumber=null, rfOrder=60, authorNames=Lu F Y, Zhang B M, Hou Y F, Xiong X, Dong C R, Lu W B, journalName=Agronomy, refType=null, unstructuredReference=Lu F Y,Zhang B M,Hou Y F,Xiong X,Dong C R,Lu W B,et al. 2025. A spatiotemporal attention-guided graph neural network for precise hyperspectral estimation of corn nitrogen content. Agronomy,15(5): #1041 [DOI: 10.3390/agronomy15051041], articleTitle=A spatiotemporal attention-guided graph neural network for precise hyperspectral estimation of corn nitrogen content, refAbstract=null), Reference(id=1322961477505778130, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=6288, pageEnd=6296, url=null, language=null, rfNumber=null, rfOrder=61, authorNames=Luo F L, Liu Y, Gong X W, Nan Z X, Guo T, journalName=null, refType=null, unstructuredReference=Luo F L,Liu Y,Gong X W,Nan Z X and Guo T. 2024. EMVCC: enhanced multi-view contrastive clustering for hyperspectral images//Proceedings of the 32nd ACM International Conference on Multimedia. Melbourne,Australia: ACM: 6288-6296 [DOI: 10.1145/3664647.3681600], articleTitle=EMVCC: enhanced multi-view contrastive clustering for hyperspectral images, refAbstract=null), Reference(id=1322961477803573716, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=124, issue=null, pageStart=null, pageEnd=103291, url=null, language=null, rfNumber=null, rfOrder=62, authorNames=Luo S, Qian Y R, Bai L, Fan Y Y, Wang Y X, Kong W Q, journalName=Information Fusion, refType=null, unstructuredReference=Luo S,Qian Y R,Bai L,Fan Y Y,Wang Y X and Kong W Q. 2025. Deep learning-based hyperspectral and multispectral fusion techniques: review,optimization,and perspectives. Information Fusion,124: #103291 [DOI: 10.1016/j.inffus.2025.103291], articleTitle=Deep learning-based hyperspectral and multispectral fusion techniques: review,optimization,and perspectives, refAbstract=null), Reference(id=1322961477870682581, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=null, rfOrder=63, authorNames=Lyu G H, Gao X, Chi Q, Zhao G X, Dong A M, Li W, journalName=null, refType=null, unstructuredReference=Lyu G H,Gao X,Chi Q,Zhao G X,Dong A M and Li W. 2025. SSFSL: self-supervised and few-shot learning for cross-domain hyperspectral image classification//Proceedings of 2025 ICASSP IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Hyderabad,India: IEEE: 1-5 [DOI: 10.1109/ICASSP49660.2025.10889995], articleTitle=SSFSL: self-supervised and few-shot learning for cross-domain hyperspectral image classification, refAbstract=null), Reference(id=1322961478223004118, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=null, pageStart=11, pageEnd=26, url=null, language=null, rfNumber=null, rfOrder=64, authorNames=Ma J Y, Yu W, Liang P W, Li C, Jiang J J, journalName=Information Fusion, refType=null, unstructuredReference=Ma J Y,Yu W,Liang P W,Li C and Jiang J J. 2019. FusionGAN: a generative adversarial network for infrared and visible image fusion. Information Fusion,48: 11-26 [DOI: 10.1016/j.inffus.2018.09.004], articleTitle=FusionGAN: a generative adversarial network for infrared and visible image fusion, refAbstract=null), Reference(id=1322961479787479511, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=24, issue=2, pageStart=152, pageEnd=164, url=null, language=null, rfNumber=null, rfOrder=65, authorNames=Maes W H, Steppe K, journalName=Trends in Plant Science, refType=null, unstructuredReference=Maes W H and Steppe K. 2019. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends in Plant Science,24(2): 152-164 [DOI: 10.1016/j.tplants.2018.11.007], articleTitle=Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture, refAbstract=null), Reference(id=1322961479904920024, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=124, issue=null, pageStart=40, pageEnd=53, url=null, language=null, rfNumber=null, rfOrder=66, authorNames=Makki I, Younes R, Francis C, Bianchi T, Zucchetti M, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference=Makki I,Younes R,Francis C,Bianchi T and Zucchetti M. 2017. A survey of landmine detection using hyperspectral imaging. ISPRS Journal of Photogrammetry and Remote Sensing,124: 40-53 [DOI: 10.1016/j.isprsjprs.2016.12.009], articleTitle=A survey of landmine detection using hyperspectral imaging, refAbstract=null), Reference(id=1322961479976223193, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=4, pageStart=120, pageEnd=141, url=null, language=null, rfNumber=null, rfOrder=67, authorNames=Manolakis D, Golowich S, DiPietro R S, journalName=IEEE Signal Processing Magazine, refType=null, unstructuredReference=Manolakis D,Golowich S and DiPietro R S. 2014. Long-wave infrared hyperspectral remote sensing of chemical clouds: a focus on signal processing approaches. IEEE Signal Processing Magazine,31(4): 120-141 [DOI: 10.1109/msp.2013.2294804], articleTitle=Long-wave infrared hyperspectral remote sensing of chemical clouds: a focus on signal processing approaches, refAbstract=null), Reference(id=1322961480081080794, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2021, volume=80, issue=1, pageStart=37, pageEnd=49, url=null, language=null, rfNumber=null, rfOrder=68, authorNames=Martin-Gallausiaux C, Marinelli L, Blottière H M, Larraufie P, Lapaque N, journalName=Proceedings of the Nutrition Society, refType=null, unstructuredReference=Martin-Gallausiaux C,Marinelli L,Blottière H M,Larraufie P and Lapaque N. 2021. SCFA: mechanisms and functional importance in the gut. Proceedings of the Nutrition Society,80(1): 37-49 [DOI: 10.1017/S0029665120006916], articleTitle=SCFA: mechanisms and functional importance in the gut, refAbstract=null), Reference(id=1322961480366293467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=9102, pageEnd=9114, url=null, language=null, rfNumber=null, rfOrder=69, authorNames=Mazzia V, Khaliq A, Salvetti F, Chiaberge M, journalName=IEEE Access, refType=null, unstructuredReference=Mazzia V,Khaliq A,Salvetti F and Chiaberge M. 2020. Real-time apple detection system using embedded systems with hardware accelerators: an edge AI application. IEEE Access,8: 9102-9114 [DOI: 10.1109/ACCESS.2020.2964608], articleTitle=Real-time apple detection system using embedded systems with hardware accelerators: an edge AI application, refAbstract=null), Reference(id=1322961480466956764, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2004, volume=42, issue=8, pageStart=1778, pageEnd=1790, url=null, language=null, rfNumber=null, rfOrder=70, authorNames=Melgani F, Bruzzone L, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Melgani F and Bruzzone L. 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing,42(8): 1778-1790 [DOI: 10.1109/TGRS.2004.831865], articleTitle=Classification of hyperspectral remote sensing images with support vector machines, refAbstract=null), Reference(id=1322961480727003613, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2505.16373.pdf, language=null, rfNumber=null, rfOrder=71, authorNames=Meng G, Cai Z N, Tu J Y, Wang Y Y, Li C X, Huang Y, journalName=null, refType=null, unstructuredReference=Meng G,Cai Z N,Tu J Y,Wang Y Y,Li C X,Huang Y,et al. 2025. PCMamba: physics-informed cross-modal state space model for dual-camera compressive hyperspectral imaging [EB/OL]. [2026-04-01]., articleTitle=PCMamba: physics-informed cross-modal state space model for dual-camera compressive hyperspectral imaging, refAbstract=null), Reference(id=1322961480789918174, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=160, issue=null, pageStart=97, pageEnd=106, url=null, language=null, rfNumber=null, rfOrder=72, authorNames=Osco L P, Arruda M D S D, Marcato Junior J, da Silva N B, Ramos A P M, Moryia É A S, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference=Osco L P,Arruda M D S D,Marcato Junior J,da Silva N B,Ramos A P M,Moryia É A S,et al. 2020. A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing,160: 97-106 [DOI: 10.1016/j.isprsjprs.2019.12.010], articleTitle=A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery, refAbstract=null), Reference(id=1322961481146434015, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2601.22581.pdf, language=null, rfNumber=null, rfOrder=73, authorNames=Paeedeh N, Pratama M, Shiddiqi A, Cao Z H, Prasad M, Jatmiko W, journalName=null, refType=null, unstructuredReference=Paeedeh N,Pratama M,Shiddiqi A,Cao Z H,Prasad M and Jatmiko W. 2026. Cross-domain few-shot learning for hyperspectral image classification based on Mixup foundation model [EB/OL]. [2026-04-01]., articleTitle=Cross-domain few-shot learning for hyperspectral image classification based on Mixup foundation model, refAbstract=null), Reference(id=1322961481213542880, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2507.05730.pdf, language=null, rfNumber=null, rfOrder=74, authorNames=Pant A, Baniya A A, Lee T K, Aryal S, journalName=null, refType=null, unstructuredReference=Pant A,Baniya A A,Lee T K and Aryal S. 2025. Hyperspectral anomaly detection methods: a survey and comparative study [EB/OL]. [2026-04-01]., articleTitle=Hyperspectral anomaly detection methods: a survey and comparative study, refAbstract=null), Reference(id=1322961481272263137, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=170, issue=null, pageStart=null, pageEnd=105900, url=null, language=null, rfNumber=null, rfOrder=75, authorNames=Peng X, Wang P T, Zhou K, Yan Z P, Zhong X G, Zhao C, journalName=Automation in Construction, refType=null, unstructuredReference=Peng X,Wang P T,Zhou K,Yan Z P,Zhong X G and Zhao C. 2025. Bridge defect detection using small sample data with deep learning and hyperspectral imaging. Automation in Construction,170: #105900 [doi: 10.1016/j.autcon.2024.105900], articleTitle=Bridge defect detection using small sample data with deep learning and hyperspectral imaging, refAbstract=null), Reference(id=1322961481679110626, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=10, pageStart=null, pageEnd=2843, url=null, language=null, rfNumber=null, rfOrder=76, authorNames=Picollo M, Cucci C, Casini A, Stefani L, journalName=Sensors, refType=null, unstructuredReference=Picollo M,Cucci C,Casini A and Stefani L. 2020. Hyper-spectral imaging technique in the cultural heritage field: new possible scenarios. Sensors,20(10): #2843 [DOI: 10.3390/s20102843], articleTitle=Hyper-spectral imaging technique in the cultural heritage field: new possible scenarios, refAbstract=null), Reference(id=1322961485785334243, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=1998, volume=19, issue=5, pageStart=823, pageEnd=854, url=null, language=null, rfNumber=null, rfOrder=77, authorNames=Pohl C and van Genderen J L, journalName=International Journal of Remote Sensing, refType=null, unstructuredReference=Pohl C and van Genderen J L. 1998. Review article multisensor image fusion in remote sensing: concepts,methods and applications. International Journal of Remote Sensing,19(5): 823-854 [DOI: 10.1080/014311698215748], articleTitle=Review article multisensor image fusion in remote sensing: concepts,methods and applications, refAbstract=null), Reference(id=1322961485894386148, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=6630, pageEnd=6638, url=null, language=null, rfNumber=null, rfOrder=78, authorNames=Qiu Y H, Bai S Y, Xu T F, Liu P F, Qin H L, Li J N, journalName=null, refType=null, unstructuredReference=Qiu Y H,Bai S Y,Xu T F,Liu P F,Qin H L and Li J N. 2025. HSOD-BIT-V2: a challenging benchmark for hyperspectral salient object detection//Proceedings of the 39th AAAI Conference on Artificial Intelligence. Philadelphia,USA: AAAI Press: 6630-6638 [DOI: 10.1609/aaai.v39i6.32711], articleTitle=HSOD-BIT-V2: a challenging benchmark for hyperspectral salient object detection, refAbstract=null), Reference(id=1322961486259290598, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=2511, pageEnd=2520, url=null, language=null, rfNumber=null, rfOrder=79, authorNames=Qu Y, Qi H R, Kwan C, journalName=null, refType=null, unstructuredReference=Qu Y,Qi H R and Kwan C. 2018. Unsupervised sparse Dirichlet-net for hyperspectral image super-resolution//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA: IEEE: 2511-2520 [DOI: 10.1109/CVPR.2018.00266], articleTitle=Unsupervised sparse Dirichlet-net for hyperspectral image super-resolution, refAbstract=null), Reference(id=1322961486678720999, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=4, pageStart=60, pageEnd=88, url=null, language=null, rfNumber=null, rfOrder=80, authorNames=Rasti B, Hong D F, Hang R L, Ghamisi P, Kang X D, Chanussot J, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Rasti B,Hong D F,Hang R L,Ghamisi P,Kang X D,Chanussot J,et al. 2020. Feature extraction for hyperspectral imagery: the evolution from shallow to deep: overview and toolbox. IEEE Geoscience and Remote Sensing Magazine,8(4): 60-88 [DOI: 10.1109/MGRS.2020.2979764], articleTitle=Feature extraction for hyperspectral imagery: the evolution from shallow to deep: overview and toolbox, refAbstract=null), Reference(id=1322961487031042536, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=null, rfOrder=81, authorNames=Ren S Q, He K M, Girshick R, Sun J, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Ren S Q,He K M,Girshick R and Sun J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,39(6): 1137-1149 [DOI: 10.1109/tpami.2016.2577031], articleTitle=Faster R-CNN: towards real-time object detection with region proposal networks, refAbstract=null), Reference(id=1322961488754901481, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=17, issue=2, pageStart=277, pageEnd=281, url=null, language=null, rfNumber=null, rfOrder=82, authorNames=Roy S K, Krishna G, Dubey S R, Chaudhuri B B, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Roy S K,Krishna G,Dubey S R and Chaudhuri B B. 2020. HybridSN: exploring 3-D—2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters,17(2): 277-281 [DOI: 10.1109/lgrs.2019.2918719], articleTitle=HybridSN: exploring 3-D—2-D CNN feature hierarchy for hyperspectral image classification, refAbstract=null), Reference(id=1322961489581179370, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=21, issue=null, pageStart=null, pageEnd=5508005, url=null, language=null, rfNumber=null, rfOrder=83, authorNames=Sankararao A U G, Rajalakshmi P, Choudhary S, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Sankararao A U G,Rajalakshmi P and Choudhary S. 2024. UC-HSI: UAV-based crop hyperspectral imaging datasets and machine learning benchmark results. IEEE Geoscience and Remote Sensing Letters,21: #5508005 [DOI: 10.1109/LGRS.2024.3431644], articleTitle=UC-HSI: UAV-based crop hyperspectral imaging datasets and machine learning benchmark results, refAbstract=null), Reference(id=1322961490038358507, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=7, issue=2, pageStart=101, pageEnd=117, url=null, language=null, rfNumber=null, rfOrder=84, authorNames=Shimoni M, Haelterman R, Perneel C, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Shimoni M,Haelterman R and Perneel C. 2019. Hyperspectral imaging for military and security applications: combining myriad processing and sensing techniques. IEEE Geoscience and Remote Sensing Magazine,7(2): 101-117 [DOI: 10.1109/MGRS.2019.2902525], articleTitle=Hyperspectral imaging for military and security applications: combining myriad processing and sensing techniques, refAbstract=null), Reference(id=1322961490810110445, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=17, issue=22, pageStart=null, pageEnd=3738, url=null, language=null, rfNumber=null, rfOrder=85, authorNames=Shrestha M, Scholl V, Sampath A, Irwin J, Kropuenske T, Adams J, journalName=Remote Sensing, refType=null, unstructuredReference=Shrestha M,Scholl V,Sampath A,Irwin J,Kropuenske T,Adams J,et al. 2025. Absolute radiometric calibration evaluation of uncrewed aerial system (UAS) headwall and MicaSense sensors and improving data quality using the empirical line method. Remote Sensing,17(22): #3738 [DOI: 10.3390/rs17223738], articleTitle=Absolute radiometric calibration evaluation of uncrewed aerial system (UAS) headwall and MicaSense sensors and improving data quality using the empirical line method, refAbstract=null), Reference(id=1322961491229540846, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=19, pageStart=null, pageEnd=3136, url=null, language=null, rfNumber=null, rfOrder=86, authorNames=Sishodia R P, Ray R L, Singh S K, journalName=Remote Sensing, refType=null, unstructuredReference=Sishodia R P,Ray R L and Singh S K. 2020. Applications of remote sensing in precision agriculture: a review. Remote Sensing,12(19): #3136 [DOI: 10.3390/rs12193136], articleTitle=Applications of remote sensing in precision agriculture: a review, refAbstract=null), Reference(id=1322961491669942767, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=1, pageStart=64, pageEnd=90, url=null, language=null, rfNumber=null, rfOrder=87, authorNames=Su H J, Wu Z Y, Zhang H H, Du Q, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Su H J,Wu Z Y,Zhang H H and Du Q. 2022. Hyperspectral anomaly detection: a survey. IEEE Geoscience and Remote Sensing Magazine,10(1): 64-90 [DOI: 10.1109/MGRS.2021.3105440], articleTitle=Hyperspectral anomaly detection: a survey, refAbstract=null), Reference(id=1322961493330887152, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=6105, pageEnd=6114, url=null, language=null, rfNumber=null, rfOrder=88, authorNames=Tan M X, Le Q V, journalName=null, refType=null, unstructuredReference=Tan M X and Le Q V. 2019. EfficientNet: rethinking model scaling for convolutional neural networks//Proceedings of the 36th International Conference on Machine Learning. Long Beach,USA: PMLR: 6105-6114, articleTitle=EfficientNet: rethinking model scaling for convolutional neural networks, refAbstract=null), Reference(id=1322961493741928945, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=42, issue=2, pageStart=205, pageEnd=213, url=null, language=null, rfNumber=null, rfOrder=89, authorNames=Tang S M, Chen Y L, journalName=Transactions of the Chinese Society of Agricultural Engineering, refType=null, unstructuredReference=Tang S M and Chen Y L. 2026. Detecting citrus from multispectral remote sensing images using an improved YOLOv8 model. Transactions of the Chinese Society of Agricultural Engineering,42(2): 205-213, articleTitle=Detecting citrus from multispectral remote sensing images using an improved YOLOv8 model, refAbstract=null), Reference(id=1322961493809037810, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=42, issue=2, pageStart=205, pageEnd=213, url=null, language=null, rfNumber=null, rfOrder=90, authorNames=唐淑铭, 陈优良, journalName=农业工程学报, refType=null, unstructuredReference=唐淑铭,陈优良. 2026. 基于改进YOLOv8的多光谱遥感影像脐橙树检测方法. 农业工程学报,42(2): 205-213 [DOI: 10.11975/j.issn.1002-6819.202507057], articleTitle=基于改进YOLOv8的多光谱遥感影像脐橙树检测方法, refAbstract=null), Reference(id=1322961494262022644, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=11, issue=20, pageStart=null, pageEnd=2389, url=null, language=null, rfNumber=null, rfOrder=91, authorNames=Tapete D, Cigna F, journalName=Remote Sensing, refType=null, unstructuredReference=Tapete D and Cigna F. 2019. Detection of archaeological looting from space: methods,achievements and challenges. Remote Sensing,11(20): #2389 [DOI: 10.3390/rs11202389], articleTitle=Detection of archaeological looting from space: methods,achievements and challenges, refAbstract=null), Reference(id=1322961495457399285, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=38, issue=8/10, pageStart=2427, pageEnd=2447, url=null, language=null, rfNumber=null, rfOrder=92, authorNames=Torresan C, Berton A, Carotenuto F, Di Gennaro S F, Gioli B, Matese A, journalName=International Journal of Remote Sensing, refType=null, unstructuredReference=Torresan C,Berton A,Carotenuto F,Di Gennaro S F,Gioli B,Matese A,et al. 2017. Forestry applications of UAVs in Europe: a review. International Journal of Remote Sensing,38(8/10): 2427-2447 [DOI: 10.1080/01431161.2016.1252477], articleTitle=Forestry applications of UAVs in Europe: a review, refAbstract=null), Reference(id=1322961499639120374, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2004, volume=25, issue=10, pageStart=1893, pageEnd=1924, url=null, language=null, rfNumber=null, rfOrder=93, authorNames=Toutin T, journalName=International Journal of Remote Sensing, refType=null, unstructuredReference=Toutin T. 2004. Review article: geometric processing of remote sensing images: models,algorithms and methods. International Journal of Remote Sensing,25(10): 1893-1924 [DOI: 10.1080/0143116031000101611], articleTitle=Review article: geometric processing of remote sensing images: models,algorithms and methods, refAbstract=null), Reference(id=1322961500603810295, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=9446, pageEnd=9454, url=null, language=null, rfNumber=null, rfOrder=94, authorNames=Ulyanov D, Vedaldi A, Lempitsky V, journalName=null, refType=null, unstructuredReference=Ulyanov D,Vedaldi A and Lempitsky V. 2018. Deep image prior//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA: IEEE: 9446-9454 [DOI: 10.1109/CVPR.2018.00984], articleTitle=Deep image prior, refAbstract=null), Reference(id=1322961502147314169, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=4, pageStart=null, pageEnd=70049, url=null, language=null, rfNumber=null, rfOrder=95, authorNames=Vaddi R, Phaneendra Kumar B L N, Mitra S, Mitra S, Bruzzone L, Roy S K, journalName=WIREs Data Mining and Knowledge Discovery, refType=null, unstructuredReference=Vaddi R,Phaneendra Kumar B L N,Mitra S,Mitra S,Bruzzone L and Roy S K. 2025. From traditional to foundation models: a survey for land use and land cover hyperspectral image classification. WIREs Data Mining and Knowledge Discovery,15(4): #70049 [DOI: 10.1002/widm.70049], articleTitle=From traditional to foundation models: a survey for land use and land cover hyperspectral image classification, refAbstract=null), Reference(id=1322961502549967354, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2012, volume=14, issue=1, pageStart=112, pageEnd=128, url=null, language=null, rfNumber=null, rfOrder=96, authorNames=van der Meer F D, van der Werff H M A, van Ruitenbeek F J A, Hecker C A, Bakker W H, Noomen M F, journalName=International Journal of Applied Earth Observation and Geoinformation, refType=null, unstructuredReference=van der Meer F D,van der Werff H M A,van Ruitenbeek F J A,Hecker C A,Bakker W H,Noomen M F,et al. 2012. Multi- and hyperspectral geologic remote sensing: a review. International Journal of Applied Earth Observation and Geoinformation,14(1): 112-128 [DOI: 10.1016/j.jag.2011.08.002], articleTitle=Multi- and hyperspectral geologic remote sensing: a review, refAbstract=null), Reference(id=1322961502981980667, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=1997, volume=35, issue=3, pageStart=675, pageEnd=686, url=null, language=null, rfNumber=null, rfOrder=97, authorNames=Vermote E F, Tanré D, Deuze J L, Herman M, Morcette J J, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Vermote E F,Tanré D,Deuze J L,Herman M and Morcette J J. 1997. Second simulation of the satellite signal in the solar spectrum,6S: an overview. IEEE Transactions on Geoscience and Remote Sensing,35(3): 675-686 [DOI: 10.1109/36.581987], articleTitle=Second simulation of the satellite signal in the solar spectrum,6S: an overview, refAbstract=null), Reference(id=1322961503061672444, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2506.14696.pdf, language=null, rfNumber=null, rfOrder=98, authorNames=Wan D H, Lu R S, Fang Y, Lang X L, Shu S B, Chen J J, journalName=null, refType=null, unstructuredReference=Wan D H,Lu R S,Fang Y,Lang X L,Shu S B,Chen J J,et al. 2025. YOLOv11-RGBT: towards a comprehensive single-stage multispectral object detection framework [EB/OL]. [2026-04-01]., articleTitle=YOLOv11-RGBT: towards a comprehensive single-stage multispectral object detection framework, refAbstract=null), Reference(id=1322961503388828157, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=47, issue=8, pageStart=6427, pageEnd=6444, url=null, language=null, rfNumber=null, rfOrder=99, authorNames=Wang D, Hu M Q, Jin Y, Miao Y C, Yang J Q, Xu Y C, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Wang D,Hu M Q,Jin Y,Miao Y C,Yang J Q,Xu Y C,et al. 2025. HyperSIGMA: hyperspectral intelligence comprehension foundation model. IEEE Transactions on Pattern Analysis and Machine Intelligence,47(8): 6427-6444 [DOI: 10.1109/TPAMI.2025.3557581], articleTitle=HyperSIGMA: hyperspectral intelligence comprehension foundation model, refAbstract=null), Reference(id=1322961506823963134, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=null, pageStart=null, pageEnd=5511805, url=null, language=null, rfNumber=null, rfOrder=100, authorNames=Wang X H, Zhao K Y, Zhao X Y, Li S Y, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Wang X H,Zhao K Y,Zhao X Y and Li S Y. 2023. GTMSiam: gated transmitting-based multiscale Siamese network for hyperspectral image change detection. IEEE Geoscience and Remote Sensing Letters,20: #5511805 [DOI: 10.1109/LGRS.2023.3329348], articleTitle=GTMSiam: gated transmitting-based multiscale Siamese network for hyperspectral image change detection, refAbstract=null), Reference(id=1322961507591520767, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=17, issue=null, pageStart=14064, pageEnd=14079, url=null, language=null, rfNumber=null, rfOrder=101, authorNames=Wang Y, Wen M, Zhang H L, Sun J Y, Yang Q, Zhang Z M, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Wang Y,Wen M,Zhang H L,Sun J Y,Yang Q,Zhang Z M,et al. 2024. HSIMAE: a unified masked autoencoder with large-scale pretraining for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,17: 14064-14079 [DOI: 10.1109/JSTARS.2024.3432743], articleTitle=HSIMAE: a unified masked autoencoder with large-scale pretraining for hyperspectral image classification, refAbstract=null), Reference(id=1322961508023534080, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=63, issue=null, pageStart=null, pageEnd=5406514, url=null, language=null, rfNumber=null, rfOrder=102, authorNames=Xie Z Y, Lyu L, Gao H M, Xu S F, Xie H H, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Xie Z Y,Lyu L,Gao H M,Xu S F and Xie H H. 2025. Dual-feature attention hybrid GCN mamba network for joint hyperspectral and LiDAR classification. IEEE Transactions on Geoscience and Remote Sensing,63: #5406514 [DOI: 10.1109/TGRS.2025.3605373], articleTitle=Dual-feature attention hybrid GCN mamba network for joint hyperspectral and LiDAR classification, refAbstract=null), Reference(id=1322961508883366401, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=187, issue=null, pageStart=null, pageEnd=107311, url=null, language=null, rfNumber=null, rfOrder=103, authorNames=Xu Y C, Wang D, Zhang L F, Zhang L P, journalName=Neural Networks, refType=null, unstructuredReference=Xu Y C,Wang D,Zhang L F and Zhang L P. 2025. Dual selective fusion transformer network for hyperspectral image classification. Neural Networks,187: #107311 [DOI: 10.1016/j.neunet.2025.107311], articleTitle=Dual selective fusion transformer network for hyperspectral image classification, refAbstract=null), Reference(id=1322961509701255683, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=1, issue=14, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=104, authorNames=Xue J Z, Yu F M, Liu Y, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Xue J Z,Yu F M and Liu Y. 2026. Hyperspectral and multispectral image fusion via sparse reconstruction and cross-guidance. Journal of Image and Graphics,1-14, articleTitle=Hyperspectral and multispectral image fusion via sparse reconstruction and cross-guidance, refAbstract=null), Reference(id=1322961511370588676, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=null, rfOrder=105, authorNames=薛吉则, 俞凤梅, 刘颖, journalName=中国图象图形学报, refType=null, unstructuredReference=薛吉则,俞凤梅,刘颖. 2026. 稀疏重建与交叉引导的高光谱与多光谱图像融合. 中国图象图形学报,1-14 [DOI: 10.11834/jig.250618], articleTitle=稀疏重建与交叉引导的高光谱与多光谱图像融合, refAbstract=null), Reference(id=1322961511802601989, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1753, pageEnd=1761, url=null, language=null, rfNumber=null, rfOrder=106, authorNames=Yang J F, Fu X Y, Hu Y W, Huang Y, Ding X H, Paisley J, journalName=null, refType=null, unstructuredReference=Yang J F,Fu X Y,Hu Y W,Huang Y,Ding X H and Paisley J. 2017. PanNet: a deep network architecture for pan-sharpening//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice,Italy: IEEE: 1753-1761 [DOI: 10.1109/ICCV.2017.193], articleTitle=PanNet: a deep network architecture for pan-sharpening, refAbstract=null), Reference(id=1322961512213643782, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=4, issue=null, pageStart=null, pageEnd=1136289, url=null, language=null, rfNumber=null, rfOrder=107, authorNames=Yel S G and Tunc Gormus E, journalName=Frontiers in Remote Sensing, refType=null, unstructuredReference=Yel S G and Tunc Gormus E. 2023. Exploiting hyperspectral and multispectral images in the detection of tree species: a review. Frontiers in Remote Sensing,4: #1136289 [DOI: 10.3389/frsen.2023.1136289], articleTitle=Exploiting hyperspectral and multispectral images in the detection of tree species: a review, refAbstract=null), Reference(id=1322961513014755847, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=5, issue=2, pageStart=29, pageEnd=56, url=null, language=null, rfNumber=null, rfOrder=108, authorNames=Yokoya N, Grohnfeldt C, Chanussot J, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Yokoya N,Grohnfeldt C and Chanussot J. 2017. Hyperspectral and multispectral data fusion: a comparative review of the recent literature. IEEE Geoscience and Remote Sensing Magazine,5(2): 29-56 [DOI: 10.1109/MGRS.2016.2637824], articleTitle=Hyperspectral and multispectral data fusion: a comparative review of the recent literature, refAbstract=null), Reference(id=1322961513446769161, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2012, volume=50, issue=2, pageStart=528, pageEnd=537, url=null, language=null, rfNumber=null, rfOrder=109, authorNames=Yokoya N, Yairi T, Iwasaki A, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Yokoya N,Yairi T and Iwasaki A. 2012. Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion. IEEE Transactions on Geoscience and Remote Sensing,50(2): 528-537 [DOI: 10.1109/tgrs.2011.2161320], articleTitle=Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion, refAbstract=null), Reference(id=1322961513551626762, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=929, pageEnd=939, url=null, language=null, rfNumber=null, rfOrder=110, authorNames=Yu B H, Liang J X, Wang Z F, Fan B, Subpa-asa A, Shi B X, journalName=null, refType=null, unstructuredReference=Yu B H,Liang J X,Wang Z F,Fan B,Subpa-asa A,Shi B X,et al. 2025. Active hyperspectral imaging using an event camera//Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville,USA: IEEE: 929-939 [DOI: 10.1109/CVPR52734.2025.00095], articleTitle=Active hyperspectral imaging using an event camera, refAbstract=null), Reference(id=1322961515543921163, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=null, pageEnd=5544713, url=null, language=null, rfNumber=null, rfOrder=111, authorNames=Yu C Y, Gong B Y, Song M P, Zhao E Y, Chang C I, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Yu C Y,Gong B Y,Song M P,Zhao E Y and Chang C I. 2022. Multiview calibrated prototype learning for few-shot hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,60: #5544713 [DOI: 10.1109/TGRS.2022.3225947], articleTitle=Multiview calibrated prototype learning for few-shot hyperspectral image classification, refAbstract=null), Reference(id=1322961515636195852, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=90, pageEnd=97, url=null, language=null, rfNumber=null, rfOrder=112, authorNames=Yu T, Li L, Luo X, Li Q, journalName=null, refType=null, unstructuredReference=Yu T,Li L,Luo X and Li Q. 2023. ReM-YOLO: a new lightweight vehicle parts target detection algorithm//Proceedings of 2023 International Conference on Pattern Recognition,Machine Vision and Intelligent Algorithms (PRMVIA). Beihai,China: IEEE: 90-97 [DOI: 10.1109/PRMVIA58252.2023.00022], articleTitle=ReM-YOLO: a new lightweight vehicle parts target detection algorithm, refAbstract=null), Reference(id=1322961515984323085, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=null, pageStart=null, pageEnd=795410, url=null, language=null, rfNumber=null, rfOrder=113, authorNames=Yuan H B, Zhu J J, Wang Q F, Cheng M, Cai Z J, journalName=Frontiers in Plant Science, refType=null, unstructuredReference=Yuan H B,Zhu J J,Wang Q F,Cheng M and Cai Z J. 2022. An improved DeepLab v3+ deep learning network applied to the segmentation of grape leaf black rot spots. Frontiers in Plant Science,13: #795410 [DOI: 10.3389/fpls.2022.795410], articleTitle=An improved DeepLab v3+ deep learning network applied to the segmentation of grape leaf black rot spots, refAbstract=null), Reference(id=1322961516386976270, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2019, volume=57, issue=2, pageStart=1205, pageEnd=1218, url=null, language=null, rfNumber=null, rfOrder=114, authorNames=Yuan Q Q, Zhang Q, Li J, Shen H F, Zhang L P, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Yuan Q Q,Zhang Q,Li J,Shen H F and Zhang L P. 2019. Hyperspectral image denoising employing a spatial-spectral deep residual convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing,57(2): 1205-1218 [DOI: 10.1109/TGRS.2018.2865197], articleTitle=Hyperspectral image denoising employing a spatial-spectral deep residual convolutional neural network, refAbstract=null), Reference(id=1322961516466668047, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2603.01174.pdf, language=null, rfNumber=null, rfOrder=115, authorNames=Zakaria Sellam A, Abdeladhim Zidi F, Eddine Bekhouche S, Houhou I, Tliba M, Distante C, journalName=null, refType=null, unstructuredReference=Zakaria Sellam A,Abdeladhim Zidi F,Eddine Bekhouche S,Houhou I,Tliba M,Distante C,et al. 2026. VP-Hype: a hybrid mamba-transformer framework with visual-textual prompting for hyperspectral image classification [EB/OL]. [2026-04-01]., articleTitle=VP-Hype: a hybrid mamba-transformer framework with visual-textual prompting for hyperspectral image classification, refAbstract=null), Reference(id=1322961516835766800, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2026, volume=18, issue=7, pageStart=null, pageEnd=1003, url=null, language=null, rfNumber=null, rfOrder=116, authorNames=Zhang B J, Wang L, Yao Q W, Li K Y, Tan Q Y, journalName=Remote Sensing, refType=null, unstructuredReference=Zhang B J,Wang L,Yao Q W,Li K Y and Tan Q Y. 2026. SG-YOLO: a multispectral small-object detector for UAV imagery based on YOLO. Remote Sensing,18(7): #1003 [DOI: 10.3390/rs18071003], articleTitle=SG-YOLO: a multispectral small-object detector for UAV imagery based on YOLO, refAbstract=null), Reference(id=1322961516911264273, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=null, rfOrder=117, authorNames=Zhang H R, Xu X, journalName=Proceedings of the 2nd Asia Symposium on Image and Graphics, refType=null, unstructuredReference=Zhang H R and Xu X. 2024. A lightweight hybrid CNN-mamba network for hyperspectral image classification//Proceedings of the 2nd Asia Symposium on Image and Graphics. Sanya,China: ACM: 73-78 [DOI: 10.1145/3718441.3718452], articleTitle=A lightweight hybrid CNN-mamba network for hyperspectral image classification, refAbstract=null), Reference(id=1322961517263585810, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=26, issue=7, pageStart=3142, pageEnd=3155, url=null, language=null, rfNumber=null, rfOrder=118, authorNames=Zhang K, Zuo W M, Chen Y J, Meng D Y, Zhang L, journalName=IEEE Transactions on Image Processing, refType=null, unstructuredReference=Zhang K,Zuo W M,Chen Y J,Meng D Y and Zhang L. 2017. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing,26(7): 3142-3155 [DOI: 10.1109/TIP.2017.2662206], articleTitle=Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising, refAbstract=null), Reference(id=1322961517347471891, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=35, issue=10, pageStart=13143, pageEnd=13163, url=null, language=null, rfNumber=null, rfOrder=119, authorNames=Zhang Q, Zheng Y M, Yuan Q Q, Song M P, Yu H Y, Xiao Y, journalName=IEEE Transactions on Neural Networks and Learning Systems, refType=null, unstructuredReference=Zhang Q,Zheng Y M,Yuan Q Q,Song M P,Yu H Y and Xiao Y. 2024. Hyperspectral image denoising: from model-driven,data-driven,to model-data-driven. IEEE Transactions on Neural Networks and Learning Systems,35(10): 13143-13163 [DOI: 10.1109/TNNLS.2023.3278866], articleTitle=Hyperspectral image denoising: from model-driven,data-driven,to model-data-driven, refAbstract=null), Reference(id=1322961517422969365, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025a, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2510.01014.pdf, language=null, rfNumber=null, rfOrder=120, authorNames=Zhang W H, Jiang C Z, Dong M J, Gui J, Dong L, Gui Z P, journalName=null, refType=null, unstructuredReference=Zhang W H,Jiang C Z,Dong M J,Gui J,Dong L,Gui Z P,et al. 2025a. Revisiting adversarial training under hyperspectral image [EB/OL]. [2026-04-01]., articleTitle=Revisiting adversarial training under hyperspectral image, refAbstract=null), Reference(id=1322961517636878870, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025b, volume=18, issue=1, pageStart=null, pageEnd=2520480, url=null, language=null, rfNumber=null, rfOrder=121, authorNames=Zhang Z Q, Wang Y, Gao D H, Li H Y, Shi G M, journalName=International Journal of Digital Earth, refType=null, unstructuredReference=Zhang Z Q,Wang Y,Gao D H,Li H Y and Shi G M. 2025b. Spectral-spatial mamba adversarial defense network for hyperspectral image classification. International Journal of Digital Earth,18(1): #2520480 [DOI: 10.1080/17538947.2025.2520480], articleTitle=Spectral-spatial mamba adversarial defense network for hyperspectral image classification, refAbstract=null), Reference(id=1322961517708182039, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=17, issue=20, pageStart=null, pageEnd=3411, url=null, language=null, rfNumber=null, rfOrder=122, authorNames=Zhao X F, Zhang H, Li C X, Wang K H, Zhang Z L, journalName=Remote Sensing, refType=null, unstructuredReference=Zhao X F,Zhang H,Li C X,Wang K H and Zhang Z L. 2025. DVIF-Net: a small-target detection network for UAV aerial images based on visible and infrared fusion. Remote Sensing,17(20): #3411 [DOI: 10.3390/rs17203411], articleTitle=DVIF-Net: a small-target detection network for UAV aerial images based on visible and infrared fusion, refAbstract=null), Reference(id=1322961518156972568, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=7, pageStart=2046, pageEnd=2062, url=null, language=null, rfNumber=null, rfOrder=123, authorNames=Zhou Q Z, Guo Q, Wang H R, Li A, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Zhou Q Z,Guo Q,Wang H R and Li A. 2024. Two-discriminators-deep residual GAN hyperspectral image pan-sharpening. Journal of Image and Graphics,29(7): 2046-2062, articleTitle=Two-discriminators-deep residual GAN hyperspectral image pan-sharpening, refAbstract=null), Reference(id=1322961518245052953, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=7, pageStart=2046, pageEnd=2062, url=null, language=null, rfNumber=null, rfOrder=124, authorNames=周庆泽, 郭擎, 王海荣, 李安, journalName=中国图象图形学报, refType=null, unstructuredReference=周庆泽,郭擎,王海荣,李安. 2024. 双判别器深度残差GAN高光谱图像融合. 中国图象图形学报,29(7): 2046-2062 [DOI: 10.11834/jig.220932], articleTitle=双判别器深度残差GAN高光谱图像融合, refAbstract=null), Reference(id=1322961518479933978, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2025, volume=63, issue=null, pageStart=null, pageEnd=5531312, url=null, language=null, rfNumber=null, rfOrder=125, authorNames=Zhu M H, Wang H, Meng Y B, Xu S J, Lin Y H, Shan Z, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Zhu M H,Wang H,Meng Y B,Xu S J,Lin Y H,Shan Z,et al. 2025. Self-supervised mamba for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,63: #5531312 [DOI: 10.1109/TGRS.2025.3622597], articleTitle=Self-supervised mamba for hyperspectral image classification, refAbstract=null), Reference(id=1322961520153461275, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=null, pageStart=null, pageEnd=6001005, url=null, language=null, rfNumber=null, rfOrder=126, authorNames=Zhu S Y, Song Y H, Zhang Y, Zhang Y L, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Zhu S Y,Song Y H,Zhang Y and Zhang Y L. 2023. ECFNet: a Siamese network with fewer FPs and fewer FNs for change detection of remote-sensing images. IEEE Geoscience and Remote Sensing Letters,20: #6001005 [DOI: 10.1109/LGRS.2023.3238553], articleTitle=ECFNet: a Siamese network with fewer FPs and fewer FNs for change detection of remote-sensing images, refAbstract=null), Reference(id=1322961520245735964, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, doi=null, pmid=null, pmcid=null, year=2017, volume=5, issue=4, pageStart=8, pageEnd=36, url=null, language=null, rfNumber=null, rfOrder=127, authorNames=Zhu X X, Tuia D, Mou L C, Xia G S, Zhang L P, Xu F, journalName=IEEE Geoscience and Remote Sensing Magazine, refType=null, unstructuredReference=Zhu X X,Tuia D,Mou L C,Xia G S,Zhang L P,Xu F,et al. 2017. Deep learning in remote sensing: a comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine,5(4): 8-36 [DOI: 10.1109/MGRS.2017.2762307], articleTitle=Deep learning in remote sensing: a comprehensive review and list of resources, refAbstract=null)], funds=[Fund(id=1322961462938960271, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, awardId=null, language=EN, fundingSource=National Natural Science Foundation of China (62372379,62472359), fundOrder=null, country=null), Fund(id=1322961463106732432, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, awardId=null, language=CN, fundingSource=国家自然科学基金项目 (62372379,62472359), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322961452272845116, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=1, ext=[AuthorCompanyExt(id=1322961452281233725, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961452272845116, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Elite Institute of Engineering,Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961452318982462, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961452272845116, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学国家卓越工程师学院,西安 710100)]), AuthorCompany(id=1322961453073957184, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=2, ext=[AuthorCompanyExt(id=1322961453090734401, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453073957184, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Key Laboratory of Aerospace Intelligent Control Technology,Beijing 100854,China), AuthorCompanyExt(id=1322961453111705922, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453073957184, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 宇航智能控制技术全国重点实验室,北京 100854)]), AuthorCompany(id=1322961453233340740, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=3, ext=[AuthorCompanyExt(id=1322961453455638853, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453233340740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Aerospace Automatic Control Institute, Beijing 100854,China), AuthorCompanyExt(id=1322961453518553414, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453233340740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京航天自动控制研究所,北京 100854)]), AuthorCompany(id=1322961453875069255, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=4, ext=[AuthorCompanyExt(id=1322961453879263560, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453875069255, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Qujing Health and Medical College,Qujing 655100,China), AuthorCompanyExt(id=1322961453891846473, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453875069255, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 曲靖健康医学院,曲靖 655100)]), AuthorCompany(id=1322961453967343946, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=5, ext=[AuthorCompanyExt(id=1322961453988315467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961454302888268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学计算机学院,西安 710100)])], figs=[ArticleFig(id=1322961459059229047, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Fig.1, caption=Evolution process of airborne spectral image processing methods, figureFileSmall=lx5febpVyANlmimNBK0bUw==, figureFileBig=p/nVYxURFThyvkNHULL1Ng==, tableContent=null), ArticleFig(id=1322961459126337912, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=图1, caption=航空光谱图像处理方法演进流程, figureFileSmall=lx5febpVyANlmimNBK0bUw==, figureFileBig=p/nVYxURFThyvkNHULL1Ng==, tableContent=null), ArticleFig(id=1322961459445105017, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Fig.2, caption=Airborne spectral images for maize health condition detection ((a) drought-stressed maize (low chlorophyll,wilted);, figureFileSmall=uXWAMeD1wnMgBWQx77IL6g==, figureFileBig=F1+kCOOOv71d9laRIoU10Q==, tableContent=null), ArticleFig(id=1322961459545768314, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=图2, caption=航空光谱图像用于玉米健康情况检测

(b) healthy maize (high chlorophyll,lush); (c) hyperspectral reflectance spectra of crops)

, figureFileSmall=uXWAMeD1wnMgBWQx77IL6g==, figureFileBig=F1+kCOOOv71d9laRIoU10Q==, tableContent=null), ArticleFig(id=1322961459612877179, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Fig.3, caption=Airborne spectral images for camouflage target recognition, figureFileSmall=PGyRYzkkohJsxjY2bmvzyQ==, figureFileBig=jXZqwQOTny1n4BZj4zxMtA==, tableContent=null), ArticleFig(id=1322961459751289212, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=图3, caption=航空光谱图像用于伪装目标识别

((a) schematic diagram of camouflage targets; (b) schematic diagram of spectral curves)

, figureFileSmall=PGyRYzkkohJsxjY2bmvzyQ==, figureFileBig=jXZqwQOTny1n4BZj4zxMtA==, tableContent=null), ArticleFig(id=1322961459818398077, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Fig.4, caption=Airborne spectral images for mineral resource exploration, figureFileSmall=zASQ5uxzwhdYL4q4cmeZqg==, figureFileBig=goUXvwaYZ/WGUkQ4qD59Gg==, tableContent=null), ArticleFig(id=1322961459893895550, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=图4, caption=航空光谱图像用于矿产资源勘探, figureFileSmall=zASQ5uxzwhdYL4q4cmeZqg==, figureFileBig=goUXvwaYZ/WGUkQ4qD59Gg==, tableContent=null), ArticleFig(id=1322961459981975935, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Fig.5, caption=Airborne spectral images for cultural heritage conservation ((a) damaged artifact; (b) spectral image of the damaged artifact), figureFileSmall=gfpSMHa/cPlduJKNfClrbg==, figureFileBig=pR3EmkGyjHp8JnGQpf8c2A==, tableContent=null), ArticleFig(id=1322961460053279104, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=图5, caption=航空光谱图像用于文物保护, figureFileSmall=gfpSMHa/cPlduJKNfClrbg==, figureFileBig=pR3EmkGyjHp8JnGQpf8c2A==, tableContent=null), ArticleFig(id=1322961460132970882, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Fig.6, caption=Commonly used airborne hyperspectral image datasets, figureFileSmall=At4Y1BsBru0ANNh1Xvkg9A==, figureFileBig=69yHDmb6QIluY7zJ7L94hg==, tableContent=null), ArticleFig(id=1322961460208468355, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=图6, caption=常用航空高光谱图像数据集

((a) Indian Pines; (b) Salinas; (c) Pavia University; (d) Berlin; (e) Loukia; (f) HanChuan)

, figureFileSmall=At4Y1BsBru0ANNh1Xvkg9A==, figureFileBig=69yHDmb6QIluY7zJ7L94hg==, tableContent=null), ArticleFig(id=1322961460275577220, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Table 1, caption=Comparison of airborne multispectral and hyperspectral images, figureFileSmall=null, figureFileBig=null, tableContent=
特性多光谱图像(MSI)高光谱图像(HSI)典型应用场景示例
波段数量3~10100~300+MSI:植被指数计算;HSI:矿物精细填图
光谱分辨率低(宽波段)高(窄波段)MSI:大范围土地覆盖;HSI:伪装目标探测
数据结构2D + 少量通道3D光谱立方体MSI:实时拼接;HSI:光谱解混
数据量较小极大(GB级)MSI:机载实时处理;HSI:地面站精细分析
信噪比较高相对较低MSI:弱光环境成像;HSI:需去噪预处理
典型传感器MicaSense RedEdge、Parrot SequoiaHeadwall Nano-Hyperspec,AVIRIS-NG-
优势实时性强、处理简单光谱信息丰富、识别精度高-
局限光谱信息有限计算复杂、维数灾难-
), ArticleFig(id=1322961461965881733, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=表1, caption=

航空多光谱与高光谱图像对比

, figureFileSmall=null, figureFileBig=null, tableContent=
特性多光谱图像(MSI)高光谱图像(HSI)典型应用场景示例
波段数量3~10100~300+MSI:植被指数计算;HSI:矿物精细填图
光谱分辨率低(宽波段)高(窄波段)MSI:大范围土地覆盖;HSI:伪装目标探测
数据结构2D + 少量通道3D光谱立方体MSI:实时拼接;HSI:光谱解混
数据量较小极大(GB级)MSI:机载实时处理;HSI:地面站精细分析
信噪比较高相对较低MSI:弱光环境成像;HSI:需去噪预处理
典型传感器MicaSense RedEdge、Parrot SequoiaHeadwall Nano-Hyperspec,AVIRIS-NG-
优势实时性强、处理简单光谱信息丰富、识别精度高-
局限光谱信息有限计算复杂、维数灾难-
), ArticleFig(id=1322961462045573511, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Table 2, caption=Summary of typical public airborne spectral datasets, figureFileSmall=null, figureFileBig=null, tableContent=
名称传感器类型空间分辨率波段数量数据规模适用任务
Indian Pines机载高光谱20 m204145 × 145地物分类
Loukia机载高光谱30 m176945 × 249地物分类
Pavia Centre机载高光谱1.3 m1021 096 × 715地物分类
Pavia University机载高光谱1.3 m103610 × 340分类、解混
Salinas机载高光谱3.7 m200512 × 217农作物分类
LongKou无人机高光谱0.463 m270515 × 2 508农作物分类
HanChuan无人机高光谱0.109 1 m2741 217 × 303农作物分类
msuav500无人机多光谱厘米级4~650万+ 图像基础模型训练、精准农业
UC-HSI无人机高光谱厘米级≥ 4农作物场景精准农业、胁迫监测
), ArticleFig(id=1322961462133653896, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=表2, caption=

典型公开航空光谱数据集

, figureFileSmall=null, figureFileBig=null, tableContent=
名称传感器类型空间分辨率波段数量数据规模适用任务
Indian Pines机载高光谱20 m204145 × 145地物分类
Loukia机载高光谱30 m176945 × 249地物分类
Pavia Centre机载高光谱1.3 m1021 096 × 715地物分类
Pavia University机载高光谱1.3 m103610 × 340分类、解混
Salinas机载高光谱3.7 m200512 × 217农作物分类
LongKou无人机高光谱0.463 m270515 × 2 508农作物分类
HanChuan无人机高光谱0.109 1 m2741 217 × 303农作物分类
msuav500无人机多光谱厘米级4~650万+ 图像基础模型训练、精准农业
UC-HSI无人机高光谱厘米级≥ 4农作物场景精准农业、胁迫监测
), ArticleFig(id=1322961462267871625, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Table 3, caption=Comparison of typical intelligent processing methods for aerial spectral images, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型代表结构优势局限适用数据计算复杂度
CNNHybridSN局部特征强、计算高效长距离依赖弱多/高光谱中
TransformerSpectralFormer全局建模能力强计算开销大高光谱高
MambaMHSSMamba线性复杂度、长序列高效局部特征需优化高光谱中低
轻量网络MobileNet-YOLO实时性强、易部署光谱特征利用弱多光谱低
), ArticleFig(id=1322961462355952010, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=表3, caption=

航空光谱图像典型智能处理方法对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型代表结构优势局限适用数据计算复杂度
CNNHybridSN局部特征强、计算高效长距离依赖弱多/高光谱中
TransformerSpectralFormer全局建模能力强计算开销大高光谱高
MambaMHSSMamba线性复杂度、长序列高效局部特征需优化高光谱中低
轻量网络MobileNet-YOLO实时性强、易部署光谱特征利用弱多光谱低
), ArticleFig(id=1322961462435643787, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Table 4, caption=Summary of typical application domains and key technologies for airborne spectral images, figureFileSmall=null, figureFileBig=null, tableContent=
应用领域核心任务数据源偏好关键技术/指标代表性文献
精准农业病虫害早期预警、植物养分监测HSI光谱指纹识别(特定波段反射率变化)、红边位置位移(监测叶绿素胁迫)(Maes和Steppe,2019),(Lu等,2025)
环境与灾害监测溢油/赤潮识别、林火烟雾检测MSI/HSI 协同吸收峰特征反演(区分油种)、热异常与烟雾穿透波段组合(Fingas和Brown,1997),(Gladkikh等,2024)
军事侦察与安防伪装目标探测、化学药剂识别HSI光谱解混(亚像元级探测)、异常检测(无需先验光谱)、特定吸收峰匹配(Makki等,2017),(Manolakis等,2014)
城市与基础设施地物精细分类、建筑物变化检测MSI空间纹理分析(区分材质)、多时相差分特征、孪生网络(Liu等,2021),(Hong等,2022)
地质与矿产资源勘探矿物填图HSI诊断性吸收特征匹配、光谱角填图(Kruse等,2003)
考古与文化遗产保护地下遗迹探测MSI植被/土壤标记识别、微地貌变化检测、多模态融合(Tapete和Cigna,2019)
), ArticleFig(id=1322961462683107724, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=表4, caption=

航空光谱图像典型应用领域及关键技术总结

, figureFileSmall=null, figureFileBig=null, tableContent=
应用领域核心任务数据源偏好关键技术/指标代表性文献
精准农业病虫害早期预警、植物养分监测HSI光谱指纹识别(特定波段反射率变化)、红边位置位移(监测叶绿素胁迫)(Maes和Steppe,2019),(Lu等,2025)
环境与灾害监测溢油/赤潮识别、林火烟雾检测MSI/HSI 协同吸收峰特征反演(区分油种)、热异常与烟雾穿透波段组合(Fingas和Brown,1997),(Gladkikh等,2024)
军事侦察与安防伪装目标探测、化学药剂识别HSI光谱解混(亚像元级探测)、异常检测(无需先验光谱)、特定吸收峰匹配(Makki等,2017),(Manolakis等,2014)
城市与基础设施地物精细分类、建筑物变化检测MSI空间纹理分析(区分材质)、多时相差分特征、孪生网络(Liu等,2021),(Hong等,2022)
地质与矿产资源勘探矿物填图HSI诊断性吸收特征匹配、光谱角填图(Kruse等,2003)
考古与文化遗产保护地下遗迹探测MSI植被/土壤标记识别、微地貌变化检测、多模态融合(Tapete和Cigna,2019)
), ArticleFig(id=1322961462762799501, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=EN, label=Table 5, caption=Summary of challenges and future directions for airborne spectral intelligent processing, figureFileSmall=null, figureFileBig=null, tableContent=
挑战维度具体瓶颈问题现有应对策略未来研究方向
高质量标注样本稀缺标注成本高、公开基准少、域偏移自监督预训练、数据增强、域泛化构建大规模多场景航空光谱数据集、掩码自编码器(MAE)预训练
模型实时性不足物理机制缺失、小样本过拟合、可解释性差低秩约束、元学习、注意力可视化物理信息驱动深度网络、光谱专用可解释方法、评估基准
模型可解释性差边缘设备资源受限、高维计算负担模型剪枝、量化、知识蒸馏、硬件加速软硬件协同优化、轻量化Mamba架构、事件相机融合
模型鲁棒性不足对抗攻击、复杂环境变化、光谱扰动对抗训练、域适应跨场景自适应学习、鲁棒性防御协议、光谱归一化
空—天—地协同困难多源数据异构、通信带宽受限、跨平台迁移难、任务规划复杂特征配准、模型压缩传输、域适应跨平台自适应特征、空天地协同基准数据集、智能任务规划、物理—数据融合
), ArticleFig(id=1322961462838296974, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, language=CN, label=表5, caption=

航空光谱智能处理的挑战与未来方向总结

, figureFileSmall=null, figureFileBig=null, tableContent=
挑战维度具体瓶颈问题现有应对策略未来研究方向
高质量标注样本稀缺标注成本高、公开基准少、域偏移自监督预训练、数据增强、域泛化构建大规模多场景航空光谱数据集、掩码自编码器(MAE)预训练
模型实时性不足物理机制缺失、小样本过拟合、可解释性差低秩约束、元学习、注意力可视化物理信息驱动深度网络、光谱专用可解释方法、评估基准
模型可解释性差边缘设备资源受限、高维计算负担模型剪枝、量化、知识蒸馏、硬件加速软硬件协同优化、轻量化Mamba架构、事件相机融合
模型鲁棒性不足对抗攻击、复杂环境变化、光谱扰动对抗训练、域适应跨场景自适应学习、鲁棒性防御协议、光谱归一化
空—天—地协同困难多源数据异构、通信带宽受限、跨平台迁移难、任务规划复杂特征配准、模型压缩传输、域适应跨平台自适应特征、空天地协同基准数据集、智能任务规划、物理—数据融合
)], attaches=null, journal=Journal(id=1249023527618129992, delFlag=0, nameCn=中国图象图形学报, nameEn=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, issn=1006-8961, eissn=null, cn=11-3758, coden=CODEN ZTTXFZ, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=uirXtX858YS3zEpFXZttJA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Image and Graphics, journalRemark=null, publicationField=null, createdTime=1775720014721, updatedTime=1788951488513, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=uirXtX858YS3zEpFXZttJA==, picEn=bud7qaxfvWHeFsbyBTAiKQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1304520351199814396, language=CN, name=中国图象图形学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488542, updatedTime=1788951488542, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304520351250146045, language=EN, name=Journal of Image and Graphics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788951488554, updatedTime=1788951488554, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=e6369def-2842-41d8, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-editor&redirect_uri=https%3A%2F%2Fcjigeditor.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=9ccec05b-6bd, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-cjig-author&redirect_uri=https%3A%2F%2Fcjig.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=1e8a31c8-5434-4f78, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1249024232475115590, websiteList=[Website(id=1249025782459334881, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN, language=CN, createTime=1775720552315, createBy=18614031015, updateTime=1775720586268, updateBy=18614031015, name=中国图象图形学报-中文, tplId=1146099689490845704, title=中国图象图形学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026166254928133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=articleTextType, value=kx, createTime=1775720643819, updateTime=1775720643819, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166221373698, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=banner, value=null, createTime=1775720643811, updateTime=1775720643811, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166271705352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=grayFlag, value=0, createTime=1775720643823, updateTime=1775720643823, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166212985089, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720643809, updateTime=1775720643809, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166288482570, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=minRunFlag, value=0, createTime=1775720643827, updateTime=1775720643827, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166246539524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/file/pic, createTime=1775720643817, updateTime=1775720643817, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166280093961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=silenceFlag, value=0, createTime=1775720643825, updateTime=1775720643825, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166233956611, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1775720643814, updateTime=1775720643814, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166259122438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeColor, value=null, createTime=1775720643820, updateTime=1775720643820, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026166267511047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782459334881, code=themeStyle, value=null, createTime=1775720643822, updateTime=1775720643822, creator=18614031015, updator=18614031015)]), Website(id=1249025782681633001, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1249024232475115590, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN, language=EN, createTime=1775720552368, createBy=18614031015, updateTime=1775720607118, updateBy=18614031015, name=中国图象图形学报-英文, tplId=1146101810881728533, title=Journal of Image and Graphics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1249026195371786511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=articleTextType, value=kx, createTime=1775720650761, updateTime=1775720650761, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195355009292, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=banner, value=null, createTime=1775720650757, updateTime=1775720650757, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195392758034, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=grayFlag, value=0, createTime=1775720650766, updateTime=1775720650766, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195342426379, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=logo, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic?fileId=TDRjKTHfgAnvFKZaDA70wA==, createTime=1775720650754, updateTime=1775720650754, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195409535252, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=minRunFlag, value=0, createTime=1775720650770, updateTime=1775720650770, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195367592206, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/file/pic, createTime=1775720650760, updateTime=1775720650760, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195401146643, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=silenceFlag, value=0, createTime=1775720650768, updateTime=1775720650768, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195359203597, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1775720650758, updateTime=1775720650758, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195380175120, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeColor, value=null, createTime=1775720650763, updateTime=1775720650763, creator=18614031015, updator=18614031015), WebsiteProps(id=1249026195388563729, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1249025782681633001, code=themeStyle, value=null, createTime=1775720650765, updateTime=1775720650765, creator=18614031015, updator=18614031015)])], journalTitle=中国图象图形学报, weixinUrl=null, journalUrl=https://www.cjig.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Image and Graphics, journalPhotoCn=uirXtX858YS3zEpFXZttJA==, journalPhotoEn=bud7qaxfvWHeFsbyBTAiKQ==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.260210, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.260210, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.260210, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.260210, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1789488000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
航空光谱图像智能处理:方法、应用与挑战
收藏切换
PDF下载
赵兴兵 1 , 郭宸瑞 2, 3 , 李羽珊 4 , 张磊 5, * , 魏巍 5
中国图象图形学报 | 大模型在航空领域的智慧赋能 2026,31(9): 3097-3119
收起
收藏切换
中国图象图形学报 |大模型在航空领域的智慧赋能 2026 , 31 (9) : 3097 -3119
航空光谱图像智能处理:方法、应用与挑战
全屏
[Author(id=1322961454386774350, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xbzhao0@gmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961454458077520, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454386774350, language=EN, stringName=Xingbing Zhao, firstName=Xingbing, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National Elite Institute of Engineering,Northwestern Polytechnical University,Xi’an 710100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961454797816145, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454386774350, language=CN, stringName=赵兴兵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西北工业大学国家卓越工程师学院,西安 710100, bio={"content":"

赵兴兵,男,博士研究生,主要研究方向为小样本高光谱图像分类。E-mail:

"}, bioImg=null, bioContent=

赵兴兵,男,博士研究生,主要研究方向为小样本高光谱图像分类。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961452272845116, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=1, ext=[AuthorCompanyExt(id=1322961452281233725, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961452272845116, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Elite Institute of Engineering,Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961452318982462, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961452272845116, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西北工业大学国家卓越工程师学院,西安 710100)])]), Author(id=1322961454894285139, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=g-ch-r@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961455141749079, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454894285139, language=EN, stringName=Chenrui Guo, firstName=Chenrui, middleName=null, lastName=Guo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 State Key Laboratory of Aerospace Intelligent Control Technology,Beijing 100854,China
3 Beijing Aerospace Automatic Control Institute, Beijing 100854,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961455221440856, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961454894285139, language=CN, stringName=郭宸瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 宇航智能控制技术全国重点实验室,北京 100854
3 北京航天自动控制研究所,北京 100854, bio={"content":"

郭宸瑞,男,工程师,主要研究方向为目标检测和多模态大模型。E-mail:

"}, bioImg=null, bioContent=

郭宸瑞,男,工程师,主要研究方向为目标检测和多模态大模型。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453073957184, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=2, ext=[AuthorCompanyExt(id=1322961453090734401, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453073957184, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Key Laboratory of Aerospace Intelligent Control Technology,Beijing 100854,China), AuthorCompanyExt(id=1322961453111705922, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453073957184, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 宇航智能控制技术全国重点实验室,北京 100854)]), AuthorCompany(id=1322961453233340740, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=3, ext=[AuthorCompanyExt(id=1322961453455638853, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453233340740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Aerospace Automatic Control Institute, Beijing 100854,China), AuthorCompanyExt(id=1322961453518553414, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453233340740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京航天自动控制研究所,北京 100854)])]), Author(id=1322961455275966810, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=myssgxka@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961455561179484, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455275966810, language=EN, stringName=Yushan Li, firstName=Yushan, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 Qujing Health and Medical College,Qujing 655100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961455628288349, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455275966810, language=CN, stringName=李羽珊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 曲靖健康医学院,曲靖 655100, bio={"content":"

李羽珊,女,硕士研究生,主要研究方向为目标检测和多模态图像融。E-mail:

"}, bioImg=null, bioContent=

李羽珊,女,硕士研究生,主要研究方向为目标检测和多模态图像融。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453875069255, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=4, ext=[AuthorCompanyExt(id=1322961453879263560, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453875069255, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Qujing Health and Medical College,Qujing 655100,China), AuthorCompanyExt(id=1322961453891846473, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453875069255, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 曲靖健康医学院,曲靖 655100)])]), Author(id=1322961455691202911, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=nwpuzhanglei@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322961455762506081, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455691202911, language=EN, stringName=Lei Zhang, firstName=Lei, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961457503142242, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961455691202911, language=CN, stringName=张磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 西北工业大学计算机学院,西安 710100, bio={"content":"

张磊,通信作者,男,教授,主要研究方向为小样本学习、图像生成和主动学习。E-mail:

"}, bioImg=null, bioContent=

张磊,通信作者,男,教授,主要研究方向为小样本学习、图像生成和主动学习。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453967343946, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=5, ext=[AuthorCompanyExt(id=1322961453988315467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961454302888268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学计算机学院,西安 710100)])]), Author(id=1322961457595416933, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=weiweinwpu@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322961457687691623, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961457595416933, language=EN, stringName=Wei Wei, firstName=Wei, middleName=null, lastName=Wei, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322961457758994792, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, authorId=1322961457595416933, language=CN, stringName=魏巍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5 西北工业大学计算机学院,西安 710100, bio={"content":"

魏巍,男,教授,主要研究方向为遥感目标检测、变化检测和多模态图像融合。E-mail:

"}, bioImg=null, bioContent=

魏巍,男,教授,主要研究方向为遥感目标检测、变化检测和多模态图像融合。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322961453967343946, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, xref=5, ext=[AuthorCompanyExt(id=1322961453988315467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China), AuthorCompanyExt(id=1322961454302888268, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322961427174129954, companyId=1322961453967343946, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 西北工业大学计算机学院,西安 710100)])])]
赵兴兵1 , 郭宸瑞2, 3 , 李羽珊4 , 张磊5, * , 魏巍5
作者信息
  • 1 西北工业大学国家卓越工程师学院,西安 710100
  • 2 宇航智能控制技术全国重点实验室,北京 100854
  • 3 北京航天自动控制研究所,北京 100854
  • 4 曲靖健康医学院,曲靖 655100
  • 5 西北工业大学计算机学院,西安 710100
通讯作者:
作者简介:

赵兴兵,男,博士研究生,主要研究方向为小样本高光谱图像分类。E-mail:

郭宸瑞,男,工程师,主要研究方向为目标检测和多模态大模型。E-mail:

李羽珊,女,硕士研究生,主要研究方向为目标检测和多模态图像融。E-mail:

张磊,通信作者,男,教授,主要研究方向为小样本学习、图像生成和主动学习。E-mail:

魏巍,男,教授,主要研究方向为遥感目标检测、变化检测和多模态图像融合。E-mail:

Intelligent processing of airborne spectral images: methods,applications,and challenges
Xingbing Zhao1 , Chenrui Guo2, 3 , Yushan Li4 , Lei Zhang5, * , Wei Wei5
Affiliations
  • 1 National Elite Institute of Engineering,Northwestern Polytechnical University,Xi’an 710100,China
  • 2 State Key Laboratory of Aerospace Intelligent Control Technology,Beijing 100854,China
  • 3 Beijing Aerospace Automatic Control Institute, Beijing 100854,China
  • 4 Qujing Health and Medical College,Qujing 655100,China
  • 5 School of Computer Science, Northwestern Polytechnical University,Xi’an 710100,China
出版时间: 2026-09-16 doi: 10.11834/jig.260210
文章导航
收藏切换

随着无人机与机载遥感技术的快速发展,航空光谱成像在农业、环境监测及军事侦察等领域发挥着越来越重要的作用。相比卫星遥感,航空平台具有更高空间分辨率、更强机动性和更短重访周期,使其成为精细化观测的重要手段。然而,航空光谱数据具有高维、强相关和噪声复杂等特点,传统处理方法难以充分挖掘其潜在信息。本文系统梳理了航空光谱图像智能处理技术的发展脉络,重点分析深度学习与机器学习方法,涵盖光谱—空间特征提取、分类、分割、目标检测、变化检测及光谱解混等关键技术;总结多光谱与高光谱协同处理在精准农业、环境灾害监测、军事侦察以及地质勘探等场景的应用进展;深入剖析当前面临的数据稀缺与标注困难、模型泛化能力不足、实时处理约束、鲁棒性欠缺及空天地协同困难等核心挑战;围绕遥感基础模型、自监督学习、边缘智能、物理信息驱动模型以及空天地一体化协同等方向展望未来趋势。本文可为航空光谱图像智能处理领域的研究与工程应用提供系统性的参考与理论指导。本文提及的数据集已汇总至https://github.com/zhaoxb2025/Airb-spe-Img。

航空光谱图像  /  高光谱图像  /  多光谱图像  /  智能处理  /  目标检测  /  变化检测  /  分类

Airborne spectral imaging,including hyperspectral imaging (HSI) and multispectral imaging (MSI) data from unmanned aerial vehicles (UAVs) and manned aircraft,has become a cornerstone of modern remote sensing. Compared to satellites,airborne platforms offer ultra-high spatial resolution,operational flexibility,short revisit cycles,and customizable sensors. Because of these advantages,they have become indispensable for precision agriculture,environmental monitoring,military reconnaissance,urban planning,geological exploration,and cultural heritage preservation. However,airborne spectral data present unique challenges,including high dimensionality (especially for HSI with hundreds of bands),strong spectral-spatial correlations,complex noise,geometric distortions from platform motion,variable illumination,and the mixed-pixel problem. Traditional methods (e.g.,SVM,random forests,and physical models) struggle to fully exploit these data due to limited feature representation,the curse of dimensionality,and poor generalization across sensors or flight conditions. As such,this paper systematically reviews intelligent processing techniques for airborne spectral images,focusing on deep learning and advanced machine learning. First,we highlight the complementary roles of HSI and MSI,stating that HSI provides rich continuous spectra for fine material identification and sub-pixel analysis,while MSI offers higher signal-to-noise ratio,lower data volume,and better real-time performance. Their synergistic use,often in a layered strategy (MSI-based coarse detection followed by HSI-based fine identification),is a key trend. Next,we discuss in detail the preprocessing pipeline—radiometric calibration,atmospheric correction,geometric registration,denoising,and resolution enhancement—noting the shift from purely physical models to hybrid data-driven and physics-informed deep learning. The core of the review covers six intelligent processing tasks. For spectral-spatial feature extraction,we trace the evolution from 2D/3D CNNs and hybrid CNN-Transformer models to state-space models like Mamba,which have been shown to achieve linear complexity while capturing long-range spectral dependencies,balancing accuracy and efficiency for real-time scenarios. For classification and segmentation,we discuss supervised,semisupervised,few-shot,and self-supervised methods (e.g.,HybridSN,Spectral-Former,and masked spectral modeling),as well as lightweight networks (MobileNet and EfficientNet) and transfer learning dominate for MSI,with cross-domain few-shot learning addressing label scarcity. For target detection,HSI exploits subtle spectral differences for camouflaged targets and chemical agents using anomaly detection or Transformer-based detectors (e.g.,SpecDETR),while MSI leverages YOLO and Faster R-CNN for real-time object detection. In addition,multimodal fusion (visible,thermal,spectral) further improves robustness. For change detection (CD),Siamese networks,Transformers (BIT and ChangeFormer),and Mamba hybrids are applied to multitemporal images,overcoming specific challenges in distinguishing real changes from illumination/atmospheric variations and incorporating physical constraints. For spectral unmixing,autoencoders learn nonlinear mixtures but lack physical constraints (nonnegativity,sum-to-one,and energy conservation),with recent efforts embedding linear mixture or radiative transfer models into deep networks for better interpretability. For multisource fusion,we cover heterogeneous fusion (HIS + LiDAR and HIS + SAR) using multimodal Transformers or GNNs,as well as spectral-spectral fusion (HIS + MSI) to generate high-resolution hyperspectral data,outlining four collaborative strategies: HSI-guided band selection,MSI-assisted dimensionality reduction,layered cascaded processing,and end-to-end joint modeling. A dedicated section addresses real-time processing and lightweight deployment on airborne edge devices (e.g.,NVIDIA Jetson). Furthermore,we review model compression (pruning,quantization,knowledge distillation,and neural architecture search) and evaluate backbones (MobileNet,HybridSN,Mamba,and efficient Transformers) for onboard inference. While real-time HSI classification and MSI detection have been demonstrated,real-time unmixing and CD remain challenging. The paper surveys typical applications,emphasizing HSI/MSI complementarity,including precision agriculture (early disease detection,nutrient/water stress,and fruit counting),environmental and disaster monitoring (oil spills,red tides,forest fires,air pollution,and mining),military reconnaissance (camouflage target detection and chemical agents),urban and infrastructure (land cover classification,building CD,traffic,and infrastructure health),geological exploration (mineral mapping,alteration zones,and oil/gas microseepage),and archaeology (subsurface relics,surface disease analysis). Next,we identify five core challenges,namely scarcity of high-quality labeled data,insufficient model generalization,real-time constraints,and lack of interpretability (black-box models ignoring physical mechanisms),and difficulties in air-space-ground collaboration (heterogeneous data,limited bandwidth,and cross-platform transfer). Finally,we outline the following directions for future works: foundation models with self-supervised learning for spectral-spatial representation; lightweight edge intelligence via hardware-software co-design; physics-informed deep models embedding radiative transfer or mixture constraints; robust and trustworthy AI with adversarial defense and uncertainty quantification; and integrated air-space-ground collaborative observation systems for hierarchical and intelligent remote sensing. In summary,this review provides a systematic reference for researchers and engineers advancing airborne spectral image intelligent processing. The datasets mentioned in this paper have been compiled and are available at https://github.com/zhaoxb2025/Airb-spe-Img.

airborne spectral image  /  hyperspectral image  /  multispectral image  /  intelligent processing  /  object detection  /  change detection  /  classification
赵兴兵, 郭宸瑞, 李羽珊, 张磊, 魏巍. 航空光谱图像智能处理:方法、应用与挑战. 中国图象图形学报, 2026 , 31 (9) : 3097 -3119 . DOI: 10.11834/jig.260210
Xingbing Zhao, Chenrui Guo, Yushan Li, Lei Zhang, Wei Wei. Intelligent processing of airborne spectral images: methods,applications,and challenges[J]. Journal of Image and Graphics, 2026 , 31 (9) : 3097 -3119 . DOI: 10.11834/jig.260210
随着遥感技术与航空平台(如无人机、有人机)的快速发展,航空遥感已成为地球观测体系中的关键组成部分(Aasen等,2018;Adão等,2017)。相较于卫星遥感与地面观测,航空遥感在空间分辨率、时间灵活性及观测精度等方面具有显著优势。具体而言,航空平台通常能够获取厘米级甚至更高空间分辨率的数据,同时具备机动性强、重访周期短及任务定制化能力强等特点,使其在精细农业监测、灾害应急响应以及军事侦察等场景中展现出不可替代的价值(Vaddi等,2025)。在多种遥感数据类型中,光谱图像因其能够反映地物的光谱响应特性而具有独特优势。根据光谱分辨率的不同,光谱图像主要分为多光谱图像与高光谱图像(Ghamisi等,2017)。多光谱图像通常包含有限数量的宽波段(一般为4~10个),具备较高的信噪比和较低的数据维度,适用于大范围快速监测;而高光谱图像则包含上百个连续窄波段,能够精细刻画地物的光谱特征,在材料识别、成分分析及亚像元探测等任务中表现出更强能力(Bioucas-Dias等,2012;Ghamisi等,2017)。
值得注意的是,多光谱与高光谱并非相互替代,而是呈现出明显的互补关系:前者强调效率与实时性(纪璎芮 等,2026),后者侧重精细识别与物理分析能力(Yokoya等,2017)。在航空平台中,这种互补性尤为重要,因为任务需求往往在“快速响应”与“高精度分析”之间进行权衡(薛吉则 等,2026)。因此,如何充分挖掘不同光谱数据的潜力,成为航空遥感领域的重要研究问题(Yel和Tunc Gormus,2023;Cao等,2019)。
尽管航空光谱成像技术不断进步,但其数据处理仍面临诸多挑战。传统遥感图像处理方法(如支持向量机、K近邻算法及基于物理模型的方法)在一定程度上依赖人工设计特征与先验知识,存在以下局限:特征表达能力有限,难以充分刻画复杂地物的非线性光谱特征(Camps-Valls等,2014);维数灾难问题,高光谱数据维度极高导致传统方法性能下降(Bioucas-Dias等,2012);混合像元问题,由于空间分辨率限制,一个像元往往包含多种地物成分,传统线性模型难以准确描述;泛化能力不足,在不同传感器、不同飞行条件下表现不稳定(周庆泽 等,2024)。
近年来,以深度学习为代表的智能处理方法在计算机视觉与遥感领域取得了突破性进展(Ahmad等,2025)。卷积神经网络(convolutional neural network,CNN)、循环神经网络(recurrent neural network,RNN)以及Transformer等模型能够通过端到端训练自动学习高层语义特征,从而显著提升光谱图像分析性能(Ahmad等,2025)。特别是在航空光谱数据处理中,深度学习展现出以下优势:能够联合建模光谱—空间特征(Roy等,2020);可处理复杂非线性问题(如非线性光谱混合)(Dobigeon等,2014);支持多任务统一建模(Liu等,2017)。此外,自监督学习、对比学习及小样本学习等新兴技术的引入,使得在标注数据有限的情况下仍可实现高性能模型训练,为航空光谱智能处理提供了新的研究方向(Jing和Tian,2021;Chen等,2020)。因此,发展面向航空光谱图像的智能处理技术,不仅是提升遥感信息提取能力的关键路径,也是推动遥感应用向自动化与智能化发展的重要支撑(Ball等,2017;Zhu等,2017)。
目前,已有大量综述工作对光谱图像处理技术进行了系统总结,但仍存在一定局限性。Ahmad等人(2025)系统综述了从传统机器学习到Transformer和Mamba模型的高光谱图像分类技术演进,详细分析了高维数据处理、特征选择困难、空间信息利用不足、噪声鲁棒性有限等挑战。Vaddi等人(2025)从传统方法到基础模型系统梳理了土地覆盖和土地利用高光谱图像分类的技术路线。然而,多数研究主要集中于卫星遥感数据,或仅关注高光谱图像单一类型,较少从“航空平台 + 智能算法”的角度进行系统梳理。而航空光谱数据在获取方式、数据特性及应用需求方面均具有显著差异,例如:数据具有更强的动态性(受飞行姿态影响显著);场景尺度变化大(从农田到城市);对实时处理与边缘计算要求更高;多源传感器融合更加常见(如光谱 + LiDAR)(Rasti等,2020;Zhang等,2024)。本文的主要贡献在于,首次以航空平台的特殊约束与应用需求为核心,系统构建了覆盖“数据特性—核心方法—典型应用—挑战展望”全链条的综述框架,并特别突出了高光谱与多光谱协同处理、“空天地”一体化等前沿理念。
根据光谱分辨率的不同,航空光谱图像主要分为多光谱图像(multispectral image,MSI)与高光谱图像(hyperspectral image,HSI)(Ghamisi等,2017;Vaddi等,2025)。多光谱图像通常由少量离散波段构成,一般为3~10个波段,每个波段覆盖较宽的光谱范围,具有较高的信噪比和较低的数据维度,因此在数据存储与实时处理方面具有明显优势(Daniels等,2023;Shrestha等,2025)。相比之下,高光谱图像通过连续窄波段对电磁波谱进行密集采样,通常包含上百个波段,能够构建三维“光谱立方体”,从而精细刻画地物的光谱特征差异(Aasen等,2018)。高光谱与多光谱的特性比较如表1所示。从数据结构上看,多光谱图像可视为二维空间信息与少量光谱通道的组合,而高光谱图像则具有显著的高维特性,其数据量通常达到GB级甚至更高,这在提升信息表达能力的同时,也带来了存储与计算上的巨大压力。在传感器方面,多光谱系统多采用如MicaSense RedEdge或Parrot Sequoia等轻量化设备,适用于无人机快速部署(Mazzia等,2020);而高光谱系统则常见于Headwall Nano-Hyperspec或AVIRIS-NG等设备,其硬件复杂度与成本显著更高(Kruse等,2003)。
从应用角度来看,多光谱数据更适合于对实时性要求较高的任务,如植被指数计算与灾害快速评估,而高光谱数据则在精细分类、矿物识别及亚像元分析等任务中表现出更强的能力(Bioucas-Dias等,2012)。因此,在航空遥感应用中,多光谱与高光谱往往呈现出“效率优先”与“精度优先”的互补关系,二者的协同利用成为当前研究的重要方向(Yokoya等,2017)。
相较于卫星遥感数据,航空光谱图像在获取过程中更易受到平台动态变化与环境因素的影响,从而呈现出更复杂的数据特性(Torresan等,2017)。
首先,由于航空平台在飞行过程中存在持续的姿态变化(如俯仰、滚转和偏航),图像容易产生几何畸变和空间错位问题(Toutin,2004)。尤其是在推扫式高光谱成像系统中,不同扫描行对应不同的成像时刻,这种时序差异进一步加剧了图像的空间不一致性(Vermote等,1997)。
其次,光照条件的变化对航空光谱数据影响显著。由于飞行时间、太阳高度角以及云层遮挡等因素的变化,同一地物在不同时间获取的光谱响应可能存在明显差异,从而导致数据分布发生偏移,给模型泛化能力带来挑战。此外,尽管航空平台通常位于较低空域,大气影响仍不可忽视。大气散射与吸收效应会改变传感器接收到的辐射信息,同时传感器自身也可能引入条纹噪声、随机噪声以及坏波段等问题,这些因素共同降低了数据质量并增加了后续处理难度(Vermote等,1997)。
最后,混合像元问题在航空光谱图像中普遍存在。由于空间分辨率仍然有限,一个像元往往包含多种地物成分,其光谱响应为多个端元的混合结果。这种混合通常具有非线性特征,使得传统线性模型难以准确描述,从而影响分类与识别精度(Dobigeon等,2014)。
针对上述数据特性与挑战,航空光谱图像在进入高层语义分析之前,通常需要经过一系列预处理步骤,包括辐射定标、大气校正、几何校正、去噪处理以及分辨率增强等。近年来,随着深度学习的发展,这些预处理过程逐步由传统物理模型驱动转向数据驱动与物理模型融合的智能化方法(Ulyanov等,2018)。
在辐射定标与大气校正方面,传统方法通常依赖于辐射传输模型,通过建模大气散射与吸收过程实现从传感器观测值到地表反射率的转换。然而,该类方法对参数依赖较强且计算复杂。近年来,研究者提出利用卷积神经网络构建端到端映射模型,直接学习从原始数字量化值到地表反射率的转换关系。同时,基于U-Net(U-shaped network)或残差网络的结构广泛用于大气校正任务,通过结合模拟数据与实测数据进行训练,可以显著提高校正效率与精度(Cao等,2019;Yang等,2017)。
在几何校正与图像配准方面,传统方法主要依赖特征点匹配(如SIFT(scale-invariant feature transform)、SURF(speeded up robust features))或地面控制点(ground control point,GCP),但在光谱图像中,由于纹理信息较弱,这些方法的稳定性有限(Toutin,2004)。深度学习方法通过学习鲁棒特征表示,能够更好地应对复杂形变。例如,基于Transformer的模型则通过全局注意力机制提高配准精度,尤其适用于多模态数据的对齐(Jaderberg等,2015)。
在去噪与异常校正方面,传统方法通常采用主成分分析(principal component analysis,PCA)或低秩表示模型进行噪声抑制,但这些方法难以充分利用空间结构信息。近年来,基于深度学习的去噪方法取得显著进展。例如,DnCNN(Zhang等,2017)通过残差学习有效去除高斯噪声,而三维卷积神经网络则能够同时建模光谱与空间维度的信息,从而更有效地去除复杂噪声(Yuan等,2019)。此外,将低秩约束与深度网络结合的“即插即用”框架,也在高光谱去噪任务中表现出良好性能(Cao等,2019)。
在分辨率增强方面,航空光谱图像常需在空间分辨率与光谱分辨率之间进行权衡。空间超分辨率技术旨在从低分辨率高光谱图像中恢复高分辨率结果,常用方法包括基于卷积神经网络的SRCNN(super-resolution convolutional neural network)、EDSR(enhanced deep super-resolution netwo)以及基于生成对抗网络的SRGAN(super-resolution generative adversarial network)(Ledig等,2017)等。另一方面,光谱重建技术则致力于从多光谱数据恢复高光谱信息,常见方法包括自编码器、生成对抗网络以及结合低秩约束的深度模型(Qu等,2018)。这类方法不仅能够降低高光谱传感器的使用成本,还为多光谱系统提供了更强的光谱表达能力。
综合来看,航空光谱图像预处理流程通常包括数据获取、辐射与大气校正、几何配准、去噪处理以及分辨率增强等步骤。与卫星遥感相比,该流程更加依赖实时处理能力与轻量化模型设计,同时需要支持多源数据的协同处理。随着深度学习方法的引入,航空光谱图像预处理正向自动化、智能化与实时化方向发展,为后续高层语义理解奠定了重要基础。为便于研究人员快速获取数据资源,表2系统总结了航空光谱领域常用的典型公开数据集及其关键特征,以增强参考价值。
航空光谱图像智能处理的核心在于高效建模“光谱—空间”高维信息,并适应航空平台特有的动态观测条件、大尺度覆盖范围与实时处理约束。近年来,该领域的研究范式已从传统机器学习演进为以CNN、Transformer、Mamba状态空间模型及图神经网络(graph neural network,GNN)为代表的多模型融合体系,其演进过程如图1所示。本节从特征提取、分类分割、目标检测、变化检测、光谱解混以及多源融合协同6个方面,系统梳理主流方法的技术脉络与前沿进展。为清晰呈现方法差异,本文汇总核心模型对比,如表3所示。
光谱图像区别于自然图像的关键在于其同时包含精细的光谱信息与空间结构信息。高光谱图像与多光谱图像在数据特性上的差异,决定了特征提取方法的设计各有侧重,但近年来二者在技术上也呈现融合趋势。
对于高光谱图像,由于其光谱连续性强、波段数多,早期方法主要采用二维卷积神经网络(2D CNN)对空间信息建模,但难以捕捉光谱维度间的相关性(Roy等,2020)。三维卷积神经网络通过在空间与光谱维度同时进行卷积操作,实现了谱—空联合特征学习,但其计算复杂度随空间尺寸呈立方增长,限制了在航空实时场景中的应用(Li等,2017)。为兼顾效率与性能,混合模型成为主流。Roy等人(2020)提出的HybridSN先使用3D卷积提取谱—空联合特征,再通过2D CNN进行空间细化,在多个高光谱数据集上取得了优异性能。该“3D + 2D”结构在航空场景中具有良好的实用平衡性。
近年来,Transformer凭借自注意力机制捕捉长距离依赖的能力,被引入高光谱特征提取。Spectral-Former将每个波段视为一个token,通过自注意力建模波段间关系,显著提升了分类性能(Hong等,2022)。然而,正如Zhang等人(2025a)所述,该架构面临标注数据稀缺、极高光谱维度、计算开销大和模型可解释性有限等问题。针对Transformer在高光谱图像分类中的感受野限制问题,研究者提出了双选择性融合Transformer网络,通过引入动态感受野机制和选择性注意力融合策略,增强了对不同尺度地物目标的适配能力(Xu等,2025)。GNN通过构建像元图(基于空间邻接或光谱相似性)建模非欧空间关系,在复杂地物分布(如城市边界、农田边缘)中表现出较强鲁棒性,但其构图计算量较大,不适于实时处理场景。
对于多光谱图像,因其波段数少、光谱连续性弱,特征提取更侧重空间信息与轻量化(Mazzia等,2020)。常用策略包括:1)采用2D CNN结合通道注意力(如SENet(squeeze-and-excitation network))自适应加权不同波段;2)直接使用EfficientNet、MobileNet等轻量骨干网络;3)将NDVI(normalized difference vegetation index)、EVI(enhanced vegetation index)等物理指数作为附加通道输入。值得注意的是,近年来已有研究者提出面向无人机多光谱图像的预训练Vision Transformer,并针对冠层高度建模和语义分割等下游任务进行了系统评估,表明Transformer架构在多光谱领域同样具备迁移潜力,但需针对波段数少的特点进行适配。
2025年以来,以Mamba(Gu和Dao,2024)为代表的状态空间模型以其线性复杂度实现高效长序列建模,开始进入航空光谱图像处理领域(Ahmad等,2025;Liu等,2025c)。在特征提取层面,Mamba与Transformer的混合模型已被用于高光谱变化检测,在精度与效率之间取得比纯Transformer和纯CNN方法更好的平衡。MVNet网络架构将3D-CNN的局部特征提取、Transformer的全局建模能力和Mamba的线性复杂度序列建模能力融为一体,实现了高效的空间—光谱特征提取与融合,在基准数据集上取得了优异性能(Li和Ye,2025)。MHSSMamba提出了多注意力空间—光谱Mamba,通过增强光谱token并采用多头自注意力捕获波段与空间位置之间的复杂关系,在Pavia University数据集上达到98.56%的分类精度(Ahmad等,2025)。VP-Hype框架将Mamba的线性时间效率与Transformer的关系建模能力统一于混合架构中,结合3D-CNN光谱前端和视觉—文本双模态提示,在小样本条件下实现了高精度分类(Zakaria Sellam等,2026)。HyPyraMamba引入金字塔光谱注意力机制和Mamba架构,在多个基准数据集上实现了鲁棒的高光谱图像分类(Li等,2026)。
当前特征提取方法对航空动态场景(如光照变化、姿态变化)的鲁棒性仍显不足;高光谱与多光谱的特征提取缺乏统一的理论框架;轻量化与表达能力的平衡仍是难点。特别是,以Mamba和Transformer为代表的混合架构虽然性能优异,但尚未在航空实时场景中得到充分验证。
分类与分割是航空光谱图像最基础的任务。其研究经历了从传统机器学习到深度学习,再到小样本学习与自监督学习的演进过程,高光谱与多光谱在此过程中既有通用技术也有专用适配。
早期,支持向量机(support vector machine,SVM)和随机森林(random forest,RF)广泛应用于高光谱分类(Melgani和Bruzzone,2004),但这些方法依赖人工设计的特征,难以处理高维光谱数据。Chen等人(2016)首次将CNN应用于高光谱分类,实现了光谱—空间联合建模,显著提升了分类精度。Roy等人(2020) 提出的HybridSN进一步降低了计算复杂度,成为该领域的代表性方法。PatchOut方法提出了一种基于Transformer-CNN混合框架的patch-free方法,用于大规模机载高光谱图像的细粒度土地覆盖分类,避免了传统分块处理带来的边界效应和计算冗余(Ji等,2025)。
航空光谱数据标注成本高、获取困难,小样本学习因此成为研究热点。Liu等人(2019)将元学习引入高光谱分类,通过学习任务间的共性实现快速泛化;Yu等人(2022)进一步优化原型学习策略,提高了少样本场景下的稳定性。然而,研究表明,当类别间光谱相似或类内差异较大时,小样本方法的性能仍存在瓶颈(何梦瑶 等,2026)。针对小样本条件下高空间分辨率高光谱图像特征学习不全面的问题,研究者提出了基于CNN-ViT(convolutional neural network and vision Transformer)混合特征优化的方法,通过深度三维卷积网络与Vision Transformer的协同特征提取,显著提升了小样本分类精度。Paeedeh等人(2026)提出了基于Mixup基础模型的跨域小样本学习方法,通过特征混合增强基础模型的泛化能力;另有研究提出了基于解耦置信原型网络的跨域小样本分类方法,通过解耦域不变特征与域特异特征提升了跨场景适应性。SCFA(spectral context-aware frequency alignment)框架从特征对齐视角出发,集成了光谱上下文建模与跨域频率对齐,在小样本高光谱分类中取得了显著效果(Martin-Gallausiaux等,2021)。
自监督学习为利用无标签数据提供了新路径。Luo等人(2024)提出基于对比学习的高光谱特征提取方法;Wang等人(2024)借鉴MAE(masked autoencoders)(He等,2022)的思想,提出掩码光谱建模方法,实现了高效的预训练。但需指出,这些方法多直接迁移自然图像处理策略,缺乏对光谱物理特性的针对性建模。Luo等人(2024)以旋转和镜像标签作为监督信号学习空间几何多样性,并通过小样本学习获取可迁移的空间元知识。此外,SSFSL(self-supervised and few-shot learning)(Lyu等,2025)将自监督学习与小样本学习相结合,为跨域高光谱图像分类提供了新路径。Self-Supervised Mamba架构(Zhu等,2025)将Mamba的线性复杂度序列建模能力与自监督预训练相结合,展现了在高光谱图像分类中的潜力。
对于多光谱图像分割,由于其数据结构与RGB图像相似,大量沿用计算机视觉框架,如DeepLabV3(Yuan等,2022)、HRNet(high-resolution network)及EfficientNet(Tan和Le,2019)。同时,NDVI、NDWI(normalized difference water index)等光谱指数常作为附加通道输入模型,以提高对植被、水体等目标的识别能力。更前沿的可微分指数学习(如DeepNDVI)将传统指数设计转化为可训练模块,实现了物理知识与数据驱动的结合。对于多光谱的小样本场景,迁移学习和域适应方法得到广泛应用,但整体上多光谱分类的模型复杂度低于高光谱。总体而言,当前分类与分割方法仍面临以下关键问题:1)缺乏大规模标注的航空光谱数据集;2)模型跨场景泛化能力弱;3)光谱信息利用仍不充分;4)模型可解释性差。未来研究需发展光谱感知的自监督学习与基础模型,并引入物理约束以提升模型可靠性。
目标检测在军事侦察、灾害监测与安防等领域具有重要意义。面对小目标尺寸、复杂背景及伪装识别等独特挑战,高光谱与多光谱目标检测的技术路线因数据特性不同而各有侧重。
对于高光谱目标检测,由于维度高且冗余严重,通常需先降维或引入光谱注意力机制(丁晨 等,2024)。Su等人(2022)提出基于光谱异常检测的方法,用于识别背景中的异常目标。基于Transformer的检测模型)及其变体通过全局注意力机制建模目标与背景之间的关系,在复杂场景中表现出更强的鲁棒性。SpecDETR作为一种基于Transformer的高光谱点目标检测网络,在高光谱目标检测任务中展现了优越性能(Li等,2025b)。然而,该类方法的计算复杂度较高,在航空实时场景中仍面临挑战。高光谱在伪装目标检测中具有独特优势,因为伪装材料的光谱曲线与背景存在细微差异。
对于多光谱目标检测,Faster R-CNN(Ren等,2017)与YOLO(you only look once)系列得到广泛使用,且因数据结构相近而可直接迁移。Wang等人(2025)提出了一种基于YOLO的实时多光谱融合框架,结合像素级融合与动态模态平衡增强,实现了高精度的多光谱目标检测;SG-YOLO作为一种轻量高效的多光谱目标检测框架,旨在平衡精度与效率(Zhang等,2026);YOLOv11-RGBT(Wan等,2025)框架设计了6种多光谱融合模式,成功应用于YOLOv3—YOLOv12以及RT-DETR等多种模型架构,为多光谱目标检测提供了统一化的解决方案;在无人机载可见光与红外图像融合方面,DVIF-Net(dual-branch visible-infrared fusion network)基于YOLO架构设计了双分支特征提取结构,分别从可见光和红外图像中提取特征后融合检测(Zhao等,2025);REM-YOLO(Yu等,2023)框架将可见光与热红外图像融合用于全天候应急响应中的行人检测。YOLO-DBME(YOLO with dual-backbone and multi-scale enhancement)模型通过频率域增强、双分支结构优化和自适应多尺度特征平衡等策略,显著提升了多光谱图像中脐橙树的检测精度和泛化能力(唐淑铭和陈优良,2026)。
总体来看,当前目标检测方法仍面临小目标尺寸有限、伪装目标的光谱差异微弱等挑战。现有方法仍以空间信息为主导,光谱信息仅作为辅助特征,未能充分发挥“光谱主导”的检测优势,实时处理能力不足。未来研究需探索光谱主导的轻量级检测框架,并提升模型的实时性与鲁棒性。
变化检测是航空遥感的重要应用之一,广泛用于灾害监测与环境评估。航空平台因机动性强而具有显著的时效优势。高光谱与多光谱在变化检测中的方法各有侧重,但核心框架(如孪生网络、Transformer)具有共通性。
传统变化检测方法主要基于差分分析或变化向量分析(change vector analysis,CVA),但对光照变化敏感,易产生误检。Daudt等人(2018)提出全卷积孪生网络,实现了端到端的变化检测。BiT(bitemporal image Transformer)模型(Qiu等,2025)通过双分支Transformer建模双时相数据之间的全局关系;ChangeFormer进一步提升了复杂变化场景下的检测能力(Bandara和Patel,2022)。
面向多光谱的变化检测常结合NDVI等指数进行快速分析,或采用多通道CVA与轻量CNN的组合。MFTSNet模型通过融合孪生结构和多尺度特征Transformer,在遥感影像变化检测中有效提升了检测精度和地物检测完整性。面向高光谱的变化检测则更适用于精细变化识别,如矿物成分变化或植被胁迫演化(El Zaar等,2023)。混合注意力和双向门控网络被提出用于高光谱图像变化检测,通过混合注意力机制和双向门控模块有效提升了检测准确性,在多个数据集上显著优于BiT、CBANet(cross-band 2-D attention network)等主流方法。ECFNet(extraction,comparison and fusion network)模型基于孪生编码器架构,在解码器中引入空间和通道联合注意力模块增强特征表达,并利用深监督模块改善变化检测效果(Zhu等,2023)。
尽管已经取得了一些进步,当前变化检测方法仍存在以下问题:1)难以有效区分光照变化与真实变化;2)对多时相数据的建模能力不足;3)缺乏对光谱物理机制的利用。未来研究需引入语义约束与辐射传输模型,实现更鲁棒的变化判别。
光谱解混是高光谱图像分析中的核心问题,其目标是将混合像元分解为若干端元及其对应的丰度系数。需要指出,多光谱图像因波段数少、光谱分辨率低,通常不适用于精确解混,而采用软分类或概率模型替代。因此本节主要面向高光谱数据。
传统方法主要基于线性混合模型(linear mixed model,LMM)(Bioucas-Dias等,2012),该模型假设简单,但在实际复杂场景中往往失效。为此,研究者提出了非线性解混方法,如基于核函数的模型,但其表达能力仍有限。Alshahrani等人(2025)首次将自编码器引入解混任务,通过隐变量表示端元,实现了端到端的非线性解混建模;Dobigeon等人(2014)进一步研究了深度非线性解混方法,显著提升了性能。然而,这类深度方法通常缺乏物理约束(如非负性、和为1、能量守恒),导致结果的可解释性较差。近年来,研究者开始探索利用多光谱数据辅助高光谱解混的策略,通过多光谱提供的空间先验信息引导高光谱端元提取,在保持解混精度的同时降低了计算复杂度(Yokoya等,2012)。
端元提取本质上是一个不适定问题,不同方法可能得到不同的端元集合。现有研究大多忽略能量守恒与光谱混合的物理机理,使得模型在实际应用中的可靠性受到限制。未来研究需将物理模型(如辐射传输模型)嵌入神经网络,以提升解混结果的稳定性与可解释性。
多源数据融合是弥补单一数据源局限、提升航空光谱信息利用效率的重要途径。本节从异构模态融合、光谱—光谱融合以及高光谱与多光谱协同策略3个层面进行阐述。
1)异构模态融合(光谱 + 非光谱)。光谱图像常与LiDAR(light detection and ranging)、SAR(synthetic aperture radar)及RGB图像融合使用。LiDAR提供精确的三维结构信息,SAR具备全天候成像能力,而RGB图像则提供丰富的纹理信息。早期方法主要采用像素级或特征级融合(Pohl和van Genderen,1998),但难以充分挖掘跨模态的深层关系。在深度学习时代,CNN与生成对抗网络(generative adversarial network,GAN)广泛应用于融合任务,显著提升了融合效果(Ma等,2019)。近年来,多模态Transformer能够在特征空间对齐不同传感器数据,实现更高层次的信息融合。然而,由于不同模态在空间分辨率、物理成像机制上的差异,融合过程仍面临配准困难与语义不一致等挑战(Chen等,2022)。Xie等人(2025)提出将GCN与Mamba混合用于高光谱与LiDAR的联合分类,实现了跨模态特征的深度融合。
2)光谱—光谱融合(高光谱 + 多光谱)。高光谱与多光谱数据在特性上具有明显互补性:高光谱提供精细的光谱信息,多光谱提供较高的空间分辨率与实时性。Yokoya等人(2017)系统总结了两类数据的融合方法,通过融合高空间分辨率多光谱图像与高光谱图像,可生成高分辨率高光谱数据。深度学习方法进一步提升了融合质量(Luo等,2025)。
3)高光谱与多光谱协同策略。随着研究的深入,航空光谱图像处理逐渐从单一数据源向多源协同发展。典型协同策略包括:多光谱辅助高光谱降维(利用多光谱波段指导高光谱数据的波段选择或特征提取)、高光谱指导多光谱波段优化(通过学习高光谱特征优化多光谱传感器的波段组合)、分层处理(采用“多光谱快速检测/分类 + 高光谱精细确认”的级联策略)、联合建模(设计统一的深度网络,同时输入高光谱与多光谱数据进行端到端学习)(Loncan等,2015)。尽管协同处理已成为发展趋势,但仍存在关键空白:缺乏大规模、多场景的联合数据集;统一的协同建模框架尚未成熟;实时系统的工程实现困难(Meng等,2025;Yu等,2025)。
航空平台(尤其是无人机)的计算资源有限(GPU(graphics processing unit)功耗、内存、算力受限),要求算法具备低延迟、低功耗特性,这是航空光谱图像处理区别于卫星遥感的核心约束。高光谱与多光谱在实时处理上面临不同挑战,但轻量化技术具有共通性。
模型压缩技术(剪枝、量化和知识蒸馏)已广泛应用于光谱神经网络的轻量化(Hinton等,2015)。TensorRT、NCNN(nebula convolutional neural network)等推理引擎可实现机端高效部署。神经架构搜索(neural architecture search,NAS)可自动设计面向特定任务的轻量光谱网络。对于多光谱数据,MobileNet、EfficientNet-Lite等轻量骨干网络已能满足实时需求;对于高光谱数据,HybridSN相比纯3D CNN更为轻量(Roy等,2020),Mamba因其线性复杂度成为有潜力的候选,而Transformer通常需要先进行降维或采用窗口注意力机制控制计算量。轻量级混合CNN-Mamba网络被提出用于高光谱图像分类,通过结合CNN和Mamba模型的优势,有效捕获了全局和局部的谱—空特征,同时保持了较低的计算开销(Zhang和Xu,2024)。
在实时检测与分类系统方面,已有研究将YOLO的改进版本部署于无人机边缘设备(如NVIDIA Jetson系列),实现了多光谱图像的实时目标检测(Zhang等,2026)。YOLOv11n轻量级模型在无人机检测、跟踪和载荷识别任务中展现出高精度和实时性能(Kabir等,2025)。然而,高光谱图像的实时解混与变化检测仍面临较大的技术挑战。基于知识蒸馏的自监督高光谱图像分类方法通过轻量化设计实现了高效率的分类(Chi等,2022)。课程式多任务自监督方法有效提升了轻量级架构的分割性能(Carlesso等,2025)。
综合来看,航空光谱图像智能处理技术的发展呈现出3条主线:1)从监督学习向自监督/小样本学习演进,以应对标注数据稀缺问题;2)从单一模态向多源融合协同发展,以发挥不同载荷的互补优势;3)从纯数据驱动向物理约束深度模型转变,以提升可解释性与泛化能力。同时,当前研究仍面临3大核心瓶颈:1)数据瓶颈:缺乏大规模、多场景、多时相的航空光谱公开数据集;2)物理瓶颈:深度模型对光谱混合机理、辐射传输模型的嵌入不足;3)系统瓶颈:实时性、轻量化与精度的平衡尚未解决,可部署的端到端系统稀少。未来突破需在算法层面(发展光谱基础模型与自监督学习)、数据层面(构建航空光谱基准数据集)与系统层面(设计边缘智能软硬件协同方案)协同推进。
航空光谱图像智能处理技术已在多个领域展现出不可替代的应用价值。高光谱图像凭借其精细的光谱分辨能力,可实现对地物物理化学属性的直接识别;多光谱图像则以其高空间分辨率、高时效性和低成本优势,在大面积动态监测中占据主导地位。二者在不同应用场景中相互补充、协同增效。本节从精准农业、环境与灾害监测、军事侦察与安防、城市与基础设施以及地质与考古5个方面,系统梳理航空光谱图像智能处理的典型应用。航空光谱图像典型应用领域及关键技术总结如表4所示。
精准农业是航空光谱图像应用最为成熟的领域之一。无人机搭载多光谱或高光谱传感器,可快速获取作物的生长状态、养分胁迫和病虫害感染等信息,为实现变量施肥、精准灌溉和早期病害防控提供数据支撑(Maes和Steppe,2019;Sishodia等,2020)。具体而言,包含作物病害早期识别、营养与水分胁迫监测、果树计数与产量预测以及林业资源调查等方面的应用。
在作物病害早期识别方面,作物受病害侵染时,其叶片内部结构(叶绿素含量、水分含量)会发生改变,进而影响光谱反射特性。高光谱图像能够捕捉到肉眼不可见的“光谱指纹”变化,在病害显症之前实现早期识别。Liu等人(2025b)利用无人机高光谱图像在水稻稻瘟病潜伏期实现了超过90%的识别准确率。Franke等人(2005)系统比较了多光谱与高光谱在小麦条锈病检测中的性能,指出高光谱在病害早期识别方面优势明显,而多光谱更适用于大面积快速筛查。航空高光谱图像用于玉米干旱检测的实例如图2所示。
在植物养分胁迫监测方面,作物在氮、磷、钾等营养元素缺乏或水分胁迫条件下,其光谱特征(如红边位置、红谷深度)会发生规律性变化。基于多光谱植被指数的智能反演模型已成为主流方法。近年来,深度学习模型直接学习光谱—营养关联,避免了指数设计的经验性。Lu等人(2025)提出了一种结合Transformer与注意力机制的高光谱反演模型,实现了对玉米叶片氮含量的高精度估计。
在林业资源调查方面,航空高光谱能够区分树种(如松树、橡树、桉树)甚至同一树种的不同健康状态。多光谱数据则更适用于林火风险评价、森林覆盖变化监测(Dash等,2018)。此外,无人机多光谱图像结合YOLO系列检测器,已广泛应用于苹果、柑橘、油棕等果树的自动计数与产量预测(Osco等,2020)。通过多时相光谱数据,可追踪果实生长过程,并结合气象数据预测成熟期产量。
航空光谱图像在环境监测与灾害应急响应中发挥着关键作用,其灵活机动的特点使其能够快速到达灾害现场,提供高时空分辨率的灾情信息。
在溢油与赤潮监测方面,海上溢油和赤潮暴发是典型的海洋环境灾害。石油膜对水体光谱具有明显的吸收和散射特征,在短波红外波段呈现高反射。多光谱传感器(如Sentinel-2的对应波段)可快速识别溢油区域(Gladkikh等,2024)。高光谱图像则能区分不同类型石油(如原油、柴油、润滑油),为事故责任认定提供依据(Fingas和Brown,1997)。对于赤潮,高光谱可识别优势藻种(如甲藻、硅藻),预警毒素风险。在林火烟雾检测方面,航空平台搭载热红外与多光谱相机,可在火灾初期发现高温热点。红外波段对高温敏感,而短波红外对烟雾穿透能力较强。基于深度学习的多光谱林火检测系统已能在无人机上实时识别火点并自动报警(Gladkikh等,2024)。在大气污染物监测方面,无人机搭载多光谱或高光谱传感器,可对工厂烟囱排放、扬尘、焚烧秸秆等大气污染源进行立体监测。通过反演气溶胶光学厚度和污染物浓度(如PM2.5、NO₂),为环保执法提供证据(段为民 等,2020)。在矿区环境监测方面,高光谱图像能够识别矿区重金属污染导致的植被胁迫(如“红边蓝移”现象),圈定污染范围。多光谱则适用于尾矿库扩容、植被恢复进度等动态监测。
航空光谱图像在军事领域具有独特的应用价值,尤其体现在伪装目标探测(如图3所示)、化学战剂识别和战场环境感知等方面。
在伪装目标探测方面,传统可见光/红外侦察难以识别涂有伪装漆或覆盖伪装网的目标,因为这些伪装材料在RGB和热红外波段与背景相似。然而,伪装材料的光谱曲线与天然植被、土壤存在细微差异,高光谱图像能够通过光谱解混或异常检测算法暴露这些差异(Makki等,2017)。Shimoni等人(2019)系统评估了高光谱在军事伪装探测中的效能,证明其较全色和热红外图像具有显著优势。深度学习增强的光谱异常检测方法进一步提高了探测率,降低了虚警率(Pant等,2025)。
在化学药剂与爆炸物识别方面,某些化学战剂(如沙林、芥子气)和爆炸物残留具有特征光谱吸收峰(主要在长波红外波段)。机载高光谱传感器可在安全距离外被动探测这些物质,为防化侦察提供新手段(Manolakis等,2014)。在战场环境感知方面,多光谱图像可用于快速区分军事目标(坦克、车辆、人员)与背景,支持目标跟踪和战场态势生成。结合深度学习检测器,多光谱无人机可实现对地面移动目标的实时锁定(Cao等,2025)。在反恐与安防方面,在大型活动安保中,无人机多光谱/高光谱可发现藏匿于人群中的异常热源(如隐藏武器)或可疑化学物质。多光谱与热红外融合方法已应用于夜间安防巡逻。
航空光谱图像在城市规划、交通监测和基础设施健康评估等方面具有广泛应用前景。
在城市地物精细分类方面,高光谱图像能够区分不同材质的屋顶(金属、沥青、瓦片)、道路(沥青、混凝土)、植被(草坪、树木)等,为城市热岛分析、径流估算提供基础数据;多光谱图像则适用于大范围土地利用分类。深度学习分类器(如HybridSN、Spectral-Former)在城市高光谱数据上已达到90%以上的总体精度(Roy等,2020;Hong等,2022)。
在建筑物变化检测方面,多时相航空多光谱图像结合孪生网络,可自动检测新建、拆除或改建的建筑物,服务于城市规划监察和违章建筑识别(Liu等,2021)。高光谱变化检测能够识别建筑物表面材料的变化,提供更精细的信息。在道路与交通监测方面,无人机多光谱图像可用于交通流量统计、车辆类型识别(轿车、卡车、公交车)。近红外波段对路面和车辆的区分度较高,有助于提高检测精度(Doornbos和Babur,2025;Maes和Steppe,2019);高光谱则能检测路面油污、积水等危险因素。在基础设施健康评估方面,利用高光谱图像检测桥梁、大坝以及管道等基础设施的表面腐蚀、渗漏和材料老化。不同腐蚀产物具有特征光谱,可实现非接触式评估(Peng等,2025)。
航空光谱图像在地质调查和矿产勘探中具有悠久应用历史,是遥感地质学的重要技术手段。
在矿物填图方面,不同矿物在短波红外和热红外波段具有诊断性吸收特征。高光谱图像能够逐像元识别矿物种类,生成矿物分布图(Kruse等,2003)。深度学习方法的引入提高了矿物识别的自动化程度和抗干扰能力(Hajaj等,2024)。多光谱数据(如ASTER模拟波段)也可用于主要矿物的初步识别,但精度较低。此外,多光谱图像结合CNN可对裸露岩性进行初步分类,而高光谱能够区分更细致的岩石类型(如图4所示)。在蚀变带识别方面,热液蚀变带是寻找金、铜等金属矿产的重要标志。航空高光谱能够通过光谱匹配或解混方法快速圈定蚀变带范围,大幅提高勘探效率(Bedini,2011)。在油气渗漏探测方面,油气微渗漏会导致地表土壤和植被发生光谱异常。高光谱图像可检测这些间接标志,辅助油气勘探(van der Meer等,2012)。
航空光谱图像在考古遗址探测和文化遗产监测中正发挥着越来越重要的作用。航空高光谱图像用于文物表面材料检测的实例如图5所示。
在地下遗迹探测方面,埋藏于地下的古墙、壕沟和墓葬等遗迹会改变上方土壤的水分含量、化学成分和植被生长状况,进而产生微弱的光谱异常。高光谱图像能够捕捉这些“植物标记”或“土壤标记”,实现无损考古探测(Tapete和Cigna,2019)。Adamopoulos和Rinaudo(2020)综述了多光谱和高光谱在考古中的应用,指出高光谱对微弱遗迹的识别能力优于多光谱。在文物表面分析方面,无人机搭载高光谱相机可对大型不可移动文物(如长城、石窟寺)进行表面病害检测,如风化、盐析和生物侵蚀等。不同病害具有不同的特征光谱,可实现自动分类与量化评估(Picollo等,2020)。在文化遗产监测方面,多时相多光谱图像可用于监测遗产地周边环境变化(如建设活动、植被入侵),为保护规划提供依据。
总体而言,航空光谱图像智能处理技术的应用已从早期的科研探索走向工程化落地。精准农业和林业是最成熟的应用领域,多光谱与高光谱协同作业成为标准模式;环境与灾害监测中,航空平台的快速响应能力不可替代;军事侦察与安防方面,高光谱的伪装探测能力具有独特优势;城市、地质以及考古等应用则更多体现了光谱图像对地物属性精细识别的价值。从应用角度看,高光谱与多光谱的分工日益清晰:多光谱适用于大面积、高频次、实时性要求高的任务;高光谱则适用于精细识别、早期预警和物质成分分析等对光谱分辨率要求高的场景。两者的深度融合与智能协同,将是未来应用发展的主要方向。
尽管航空光谱图像智能处理技术取得了显著进展,深度学习方法的引入极大地提升了分类、检测和解混等任务的性能,但在实际应用中仍面临诸多挑战。这些挑战既有航空光谱数据本身固有的特性所导致,也有深度学习模型在该领域适配过程中产生的新问题。本节从标注数据稀缺性、模型实时性、模型可解释性、模型鲁棒性以及多平台协同性5个维度,系统梳理当前面临的核心挑战。
数据是深度学习模型性能的根本保障,然而在航空光谱图像领域,数据问题始终是制约技术发展的首要瓶颈。
1)像素级标注成本高昂。深度学习模型通常依赖大规模标注数据进行训练,但在航空光谱领域,像素级精细标注的成本极高。高光谱图像每个像元对应一条连续的光谱曲线,标注需要专业的地物知识,耗时费力。 Liu等人(2025)在构建首个高光谱遥感显著目标检测数据集时指出,该领域进展长期受限于专用数据集和方法论的匮乏,其发布的HRSSD(hyperspectral remote sensing saliency dataset)数据集包含704幅高光谱图像和5 327个像素级标注的显著目标,是目前为数不多的公开基准之一。在卫星遥感领域,HYPSO-1 Sea-Land-Cloud数据集提供了200幅高光谱图像,其中仅38幅具有像素级海/陆/云类别标注(Justo等,2023)。与ImageNet、COCO(common objects in context)等自然图像数据集动辄百万级的规模相比,航空光谱数据的标注规模存在数量级差距。针对遥感图像标注门槛高、带标签数据少的普遍问题,点—线—面多粒度大规模遥感基准数据构建范式通过主动学习框架实现了高效标注,为缓解标注困难提供了新思路。
2)公开基准数据集匮乏。航空光谱领域不仅标注数据规模小,具备广泛影响力的公开数据集也十分有限。现有高光谱分类任务主要依赖Indian Pines、Pavia University、Salinas等上世纪90年代采集的机载数据集,这些数据的光谱分辨率、空间分辨率和场景多样性已难以代表当前无人机遥感的技术水平。常用公开航空高光谱数据集如图6所示。
近年来,研究者开始构建面向特定任务的数据集。Lekhak等人(2026)发布了首个用于地雷和未爆炸物检测的无人机(unmanned aerial vehicle,UAV)可见近红外高光谱基准数据集,包含270个连续光谱波段,采集于143个模拟目标的控制测试场,填补了该领域的公开数据空白。Doornbos和Babur(2025)构建了msuav500k数据集,包含来自多种传感器(DJI Mavic 3M、DJI Phantom 4 Multispectral、MicaSense系列)的多光谱与RGB无人机图像,覆盖至少4个光谱波段,经过系统性辐射定标以保证跨传感器的一致性,旨在支持基础模型的训练与微调。在作物监测领域,UC-HSI数据集提供了无人机高光谱农作物影像,为精准农业研究提供基准(Sankararao等,2024)。然而,这些新发布的数据集往往针对特定场景或任务,跨场景、跨传感器和跨任务的通用数据集仍然缺失。
1)航空平台(尤其是无人机)的计算资源有限(GPU功耗、内存、算力受限)。要求算法具备低延迟、低功耗特性。这是航空光谱图像处理区别于卫星遥感或地面处理的核心约束。
2)机载边缘设备的资源限制问题。典型机载边缘设备如NVIDIA Jetson Xavier NX的功耗约20 W,其算力远低于桌面级GPU。在如此受限的资源条件下运行复杂的光谱深度学习模型,面临巨大挑战。模型压缩技术已被广泛采用以缓解该问题。然而,将这些技术真正集成到实用的无人机边缘智能系统中,仍有大量工程问题待解决。关于深度学习模型在此过程中面临的计算复杂度困境,在3.1节已有概述。
随着深度学习模型在航空光谱图像处理中的广泛应用,模型的“黑箱”特性日益成为制约其可信应用的关键瓶颈。在军事侦察、环境执法和医疗诊断等安全敏感领域,缺乏可解释性的模型难以获得用户信任,也限制了其在真实任务中的部署。
1)光谱物理机制的不可见性。高光谱图像的核心价值在于其连续光谱曲线能够反映地物的物质属性。然而,当前主流的深度学习方法(如CNN、Transformer、Mamba)直接将光谱波段视为独立的特征通道,其内部运算过程缺乏对光谱物理意义的显式建模。模型的决策依据往往无法回溯到具体的光谱吸收特征、反射峰位置等可解释的物理量。例如,在矿物填图任务中,一个分类正确的模型可能依据的是空间纹理而非诊断性光谱特征,这种“伪相关”会导致模型在新场景中迁移失败。
2)注意力机制的可解释性局限。虽然Transformer等架构中的注意力机制常用于可解释性的工具,但研究表明,注意力权重并不能完全反映模型的实际决策过程。在高光谱图像中,注意力机制可能过度关注空间位置而非光谱波段,导致解释结果偏离真实的物理机制(Li等,2017)。此外,不同注意力头之间的交互复杂,难以形成直观的人类可理解的解释。
3)特征可视化与归因分析的困难。相比于自然图像,高光谱图像的高维特性使得传统的特征可视化方法(如Grad-CAM、LIME(local interpretable model-agnostic explanations))面临挑战。这些方法通常需要降维预处理,而降维过程本身会损失光谱信息,导致解释结果失真(Meng等,2025)。同时,高光谱图像中相邻波段的高度相关性使得归因分析容易产生歧义,难以准确识别对决策贡献最大的光谱特征。
4)模型决策的不可审计性。在军事侦察、环境执法等场景中,模型的错误决策可能带来严重后果。缺乏可解释性的模型使得决策过程无法被审计和追查,也难以根据失败案例进行针对性改进。当前,高光谱领域的可解释性研究仍处于起步阶段,缺乏统一的评估标准和基准数据集。
随着深度学习模型在航空光谱任务中的广泛应用,模型的鲁棒性和安全性问题日益凸显。
1)对抗样本攻击的威胁。研究表明,基于深度学习的高光谱图像分类模型对对抗样本攻击高度脆弱,这构成了严重的安全风险(Doornbos和Babur,2025)。与传统RGB图像不同,高光谱数据的对抗扰动可能破坏其细微的光谱语义信息,而光谱语义恰好是高光谱图像判别性信息的核心来源。Zhang等人(2025a)研究发现,直接将在RGB图像上有效的对抗训练方法迁移至高光谱领域面临独特挑战,即高维光谱特征和波段间的强相关性使得对抗扰动更容易破坏关键的谱间一致性。该研究提出了高光谱专用的对抗训练方法AT-HARL和AT-RA,通过利用光谱特征差异和类别分布比例设计新的损失函数,以及引入光谱数据增强来缓解语义失真问题。在军事侦察、目标识别等安全敏感应用中,对抗样本攻击的防御策略研究具有重要意义。SSMADNet进一步提出了谱—空Mamba对抗防御网络,在高光谱对抗图像分类中取得了优于现有防御方法的分类精度(Zhang等,2025b)。
2)模型在复杂环境下的失效风险。航空光谱图像采集环境复杂多变,云层遮挡、雨雾天气、光照剧烈变化以及传感器噪声等因素都可能导致深度学习模型性能急剧下降。现有模型在设计时通常假设理想化的采集条件,对复杂环境因素的鲁棒性缺乏充分考虑。场景适应性不足是当前方法的突出瓶颈,在实际应用中难以保证稳定可靠地输出正确结果(Wang等,2023)。
3)光谱信息扰动对模型的影响。航空平台获取的光谱数据本身存在不确定性。无人机平台的姿态变化导致地物在视场中的几何形变,不同飞行批次之间的光照差异导致光谱反射率的一致性降低,传感器自身的热噪声也会影响光谱质量。这些扰动都会对依赖精细光谱特征的深度学习模型产生影响。
航空光谱遥感正从单一平台作业向“空—天—地”一体化协同观测的方向发展。然而,不同平台之间的数据协同面临多层面的困难,制约了光谱智能处理技术的体系化应用。
1)多源数据异构性与配准困难。卫星、无人机和地面传感器获取的光谱数据在空间分辨率、光谱分辨率、时间分辨率以及观测角度等方面存在显著差异。卫星数据覆盖范围广但分辨率低,无人机数据精细但覆盖有限,地面数据精确但离散。如何将这3类异构数据进行精确的时空配准,是实现协同观测的首要难题。由于成像几何、大气条件以及地物动态变化等因素,不同平台获取的同一地物光谱响应可能存在较大偏差,传统的特征匹配方法难以实现高精度配准。
2)通信带宽与实时协同的限制。在空天地一体化观测网络中,无人机与卫星、地面站之间的数据传输受到通信带宽的严重制约。高光谱图像数据量大,而无人机与地面站的实时通信链路往往带宽有限,难以实现原始数据的实时回传。这要求机载端具备较强的在线处理能力,能够提取关键信息后压缩传输。同时,多无人机协同观测时的数据融合、任务分配也需要高效的通信协议和分布式计算框架,当前仍缺乏成熟解决方案。
3)跨平台模型的泛化与迁移难题。在卫星数据上训练的深度学习模型往往难以直接应用于无人机数据,反之亦然。这是因为不同平台的数据分布存在显著的域偏移(如空间分辨率、光谱响应函数、信噪比等差异)(Wang等,2025)。虽然域适应和域泛化方法有所进展,但在空天地多源场景下,源域和目标域之间的差异更为复杂,现有方法难以同时适应多种平台的数据特性。此外,不同平台的光谱波段设置可能不同(如卫星高光谱与无人机高光谱的波段范围、中心波长不一致),导致模型无法直接迁移(Braham等,2025)。
4)协同观测的任务规划与资源调度复杂。实现空天地协同观测需要根据观测目标(如灾害应急、农业监测)动态规划卫星过境时间、无人机航线以及地面传感器布设。这是一个多约束优化问题,涉及气象条件、能源限制、通信窗口以及观测优先级等因素。当前,缺乏智能化的任务规划算法和协同决策框架,多数协同观测仍依赖人工经验,效率低下。
综上所述,航空光谱图像智能处理技术面临标注数据稀缺性、模型实时性、模型可解释性、模型鲁棒性以及空—天—地协同等挑战。这些挑战相互交织、彼此影响,任何单一维度的改进都难以实现系统性的突破,需要在多个层面协同推进。
针对第4节的核心挑战,本节从基础模型与自监督学习、轻量化边缘智能、物理信息驱动的深度模型、鲁棒性与可信智能以及空天地一体化协同等5个方面展望未来的研究趋势与发展路径。具体挑战与未来方向总结如表5所示。
基础模型与自监督学习的结合为航空光谱数据标注稀缺问题提供了极具潜力的解决路径。已有研究表明,在大规模无标注数据上进行自监督预训练,能够学习通用的光谱—空间特征表示,显著降低下游任务对精细标注的依赖。在架构设计上,发展“光谱适配器 + 基础骨干”的轻量架构,使模型能动态适应不同波段数的输入,同时保持较低的计算开销;在迁移策略上,推动面向高光谱的提示学习研究,设计光谱感知的提示模板,实现零样本或少样本条件下的快速任务迁移。此外,建立统一的航空光谱基础模型评估基准,规范不同模型在分类、检测和解混等任务上的性能对比,促进该领域的健康发展。
针对机载边缘设备资源受限与高维数据计算负担之间的矛盾,轻量化边缘智能是关键解决路径。此外,事件相机与光谱成像的结合为实时光谱感知开辟了新方向。事件相机具有微秒级时间分辨率、极低功耗和低数据带宽的优势,可在动态场景中高效捕获光谱变化。未来研究应注重软硬件协同优化:算法层面,结合神经架构搜索自动设计面向特定任务的专用轻量架构,并引入知识蒸馏将大模型能力迁移至小网络;硬件层面,推动事件相机、快照式高光谱相机与边缘计算芯片(如Jetson、RK3588)的深度集成;系统层面,构建“模型压缩—硬件加速—机载推理”的一体化部署流程,实现毫秒级响应。同时,需警惕轻量化对光谱物理完整性的侵蚀,应在模型“瘦身”时保留关键光谱特征。
将辐射传输模型、光谱混合模型等物理知识嵌入深度学习框架,是提升模型可解释性与泛化能力的有效路径。未来应构建“物理层”与“数据层”深度融合的新型网络架构,例如将PROSAIL辐射传输模型作为可微分模块嵌入,实现从反射率到生化参数的端到端反演。发展光谱物理约束损失函数,将光谱连续性、非负性等先验以软约束形式加入优化目标。结合可解释AI(artificial intelligence)方法,对模型的决策依据进行光谱维度的可视化分析,生成“波段重要性图谱”,增强用户信任。在标注稀缺场景下,利用物理模型提供归纳偏置;在数据充足时,通过数据驱动弥补物理模型的简化假设。此外,建立物理—数据融合模型的评估基准,量化其相较于纯数据驱动模型在可解释性和外推能力上的增益。
对抗样本攻击、复杂环境变化及光谱信息扰动对航空光谱智能模型的鲁棒性构成严峻挑战。面对对抗样本攻击的威胁问题,未来应发展面向高光谱数据特性的对抗攻击与防御统一理论,研究物理可实现的对抗扰动,并开发轻量级在线防御机制。面对模型失效问题,探索多源域自适应的统一框架,结合元学习使模型快速适应未知场景。针对光谱信息扰动,设计对扰动不敏感的特征提取方法,例如引入光谱归一化层消除增益变化,采用对抗性数据增强模拟真实扰动,或利用生成模型进行光谱重建与校正。
实现空—天—地协同是实现航空光谱遥感从单点观测走向体系化应用的关键。当前面临多源数据异构、通信带宽受限、跨平台模型迁移难以及任务规划复杂等多重挑战。未来应发展跨平台自适应特征表示方法,例如采用对抗域适应学习平台无关的光谱—空间特征,或设计光谱超分辨率网络将多光谱升采样至与高光谱一致的光谱分辨率;构建覆盖卫星、无人机以及地面平台的多源、多时相和多场景协同基准数据集,标注跨平台的对应关系,为跨平台模型训练与评估提供基础。在通信架构上,研究适用于空天地协同的轻量化通信协议和分布式计算框架:机载端执行初步处理与特征压缩,仅传输关键信息;地面站进行精细化分析与模型更新。在跨尺度融合方面,探索物理模型与数据驱动相结合的方法。最终建立“天基粗查—空基详查—地基验证”的分层协同观测模式,形成高效的应急响应机制,在灾害监测、精准农业和环境执法等重大需求中发挥重要作用。
本文从数据特性与预处理、核心方法、典型应用、挑战及展望5个维度,系统构建了航空光谱图像智能处理技术的完整知识框架。本文的主要贡献与核心结论如下:
1)揭示了该领域技术演进的3条鲜明主线。 (1)从监督学习向自监督/小样本学习演进,以应对航空光谱数据标注稀缺的瓶颈;(2)从单一模态向多源融合协同发展,充分发挥高光谱与多光谱的互补优势;(3)从纯数据驱动向物理约束深度模型转变,以提升模型的可解释性与泛化能力。
2)明确提出了高光谱与多光谱分工协同的应用范式。从应用角度看,二者并非替代关系,其分工日益清晰:多光谱凭借高时效、低成本的优势,主导大面积实时监测;高光谱则凭借精细光谱分辨能力,在病害早期诊断、矿物填图以及伪装探测等精细识别场景中不可替代。“多光谱快速筛查 + 高光谱精细确认”的分层作业模式,已成为精准农业、军事侦察等领域的事实标准。
3)深入剖析了制约技术落地的5大核心瓶颈。 当前面临数据稀缺、物理建模缺失、实时性受限、鲁棒性不足及空天地协同困难等挑战,这些瓶颈相互交织,需在算法、数据与系统层面协同突破。
4)系统展望了未来的5个突破方向。未来研究将围绕基础模型与自监督学习、轻量化边缘智能、物理信息驱动深度模型、可信智能以及空天地一体化协同展开。随着这些瓶颈的突破,航空光谱图像智能处理技术将推动遥感应用从单点观测走向体系化智能感知,为精准农业、环境监测以及军事侦察等领域注入新的活力。
  • 国家自然科学基金项目 (62372379,62472359)
参考文献 引证文献
排序方式:
Aasen H,Honkavaara E,Lucieer A and Zarco-Tejada P J. 2018. Quantitative remote sensing at ultra-high resolution with UAV spectroscopy: a review of sensor technology,measurement procedures,and data correction workflows. Remote Sensing,10(7): #1091 [DOI: 10.3390/rs10071091]
Adamopoulos E and Rinaudo F. 2020. UAS-based archaeological remote sensing: review,meta-analysis and state-of-the-art. Drones,4(3): #46 [DOI: 10.3390/drones4030046]
Adão T,Hruška J,P􀅡dua L,Bessa J,Peres E,Morais R,et al. 2017. Hyperspectral imaging: a review on UAV-based sensors,data processing and applications for agriculture and forestry. Remote Sensing,9(11): #1110 [DOI: 10.3390/rs9111110]
Ahmad M,Butt M H F,Usama M,Altuwaijri H A,Mazzara M,Distefano S,et al. 2025. Multi-head spatial-spectral mamba for hyperspectral image classification. Remote Sensing Letters,16(4): 339-353 [DOI: 10.1080/2150704X.2025.2461330]
Alshahrani A A,Bchir O and Ben Ismail M M. 2025. Autoencoder-based hyperspectral unmixing with simultaneous number-of-endmembers estimation. Sensors,25(8): #2592 [DOI: 10.3390/s25082592]
Ball J E,Anderson D T and Chan C S. 2017. Comprehensive survey of deep learning in remote sensing: theories,tools,and challenges for the community. Journal of Applied Remote Sensing,11(4): #042609 [DOI: 10.1117/1.jrs.11.042609]
Bandara W G C and Patel V M. 2022. A transformer-based Siamese network for change detection//2022 IGARSS IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur,Malaysia: IEEE: 207-210 [DOI: 10.1109/IGARSS46834.2022.9883686]
Bedini E. 2011. Mineral mapping in the Kap Simpson complex,central East Greenland,using HyMap and ASTER remote sensing data. Advances in Space Research,47(1): 60-73 [DOI: 10.1016/j.asr.2010.08.021]
Bioucas-Dias J M,Plaza A,Dobigeon N,Parente M,Du Q,Gader P,et al. 2012. Hyperspectral unmixing overview: geometrical,statistical,and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,5(2): 354-379 [DOI: 10.1109/JSTARS.2012.2194696]
Braham N A A,Albrecht C M,Mairal J,Chanussot J,Wang Y and Zhu X X. 2025. SpectralEarth: training hyperspectral foundation models at scale. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,18: 16780-16797 [DOI: 10.1109/JSTARS.2025.3581451]
Camps-Valls G,Tuia D,Bruzzone L and Benediktsson J A. 2014. Advances in hyperspectral image classification: earth monitoring with statistical learning methods. IEEE Signal Processing Magazine,31(1): 45-54 [DOI: 10.1109/msp.2013.2279179]
Cao C H,Yu J,Zhou C Y,Hu K,Xiao F and Gao X P. 2019. Hyperspectral image denoising via subspace-based nonlocal low-rank and sparse factorization. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,12(3): 973-988 [DOI: 10.1109/JSTARS.2019.2896031]
Cao S H,Wang T,Li T and Fei S M. 2025. UAV real-time target detection and tracking algorithm based on improved KCF and YOLOv5s_MSES. Machines,13(5): #364 [DOI: 10.3390/machines13050364]
Carlesso H,Mothe J and Ionescu R T. 2025. Curriculum multi-task self-supervision improves lightweight architectures for onboard satellite hyperspectral image segmentation [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2509.13229.pdf
Chen J Y,Frey E C,He Y F,Segars W P,Li Y and Du Y. 2022. TransMorph: transformer for unsupervised medical image registration. Medical Image Analysis,82: #102615 [DOI: 10.1016/j.media.2022.102615]
Chen T,Kornblith S,Norouzi M and Hinton G E. 2020. A simple framework for contrastive learning of visual representations//Proceedings of the 37th International Conference on Machine Learning. [s.l.]: PMLR: 1597-1607
Chen Y,Jiang H,Li C,Jia X and Ghamisi P. 2016. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing,54(10): 6232-6251 [DOI: 10.1109/TGRS.2016.2584107]
Chi Q,Lyu G H,Zhao G X and Dong X J. 2022. A novel knowledge distillation method for self-supervised hyperspectral image classification. Remote Sensing,14(18): #4523 [DOI: 10.3390/rs14184523]
Daniels L,Eeckhout E,Wieme J,Dejaegher Y,Audenaert K and Maes W H. 2023. Identifying the optimal radiometric calibration method for UAV-based multispectral imaging. Remote Sensing,15(11): #2909 [DOI: 10.3390/rs15112909]
Dash J P,Pearse G D and Watt M S. 2018. UAV multispectral imagery can complement satellite data for monitoring forest health. Remote Sensing,10(8): #1216 [DOI: 10.3390/rs10081216]
Daudt R C,Le Saux B and Boulch A. 2018. Fully convolutional Siamese networks for change detection//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens,Greece: IEEE: 4063-4067 [DOI: 10.1109/ICIP.2018.8451652]
Ding C,Chen J Y,Zheng M M,Zhang L,Wei W and Zhang Y N. 2024. Survey of hyperspectral image change detection method. Journal of Image and Graphics,29(6): 1714-1729
丁晨,陈静怡,郑萌萌,张磊,魏巍,张艳宁. 2024. 高光谱图像变化检测技术研究进展. 中国图象图形学报,29(6): 1714-1729 [DOI: 10.11834/jig.240031]
Dobigeon N,Tourneret J Y,Richard C,Bermudez J C M,McLaughlin S and Hero A O. 2014. Nonlinear unmixing of hyperspectral images: models and algorithms. IEEE Signal Processing Magazine,31(1): 82-94 [DOI: 10.1109/MSP.2013.2279274]
Doornbos J and Babur Ö. 2025. msuav500k: foundational dataset for multispectral and RGB uncrewed aerial vehicle imagery. Data in Brief,63: #112128 [DOI: 10.1016/j.dib.2025.112128]
Duan W M,Xiong Y H,Chen Z W,Yu G B,Liu L M,Li F Q,et al. 2020. Remote sensing and monitoring of industrial SO2 and carbon black particles with ultraviolet imaging technology. Acta Photonica Sinica,49(4): #0404002
段为民,熊远辉,陈振威,于光保,刘林美,李发泉,等. 2020. 工业SO2及碳黑颗粒紫外成像遥感监测技术. 光子学报,49(4): #0404002 [DOI: 10.3788/gzxb20204904.0404002]
El Zaar A,Assawab R,Aoulalay A,Benaya N,Bakir T,Femmam S,et al. 2023. MFTs-Net: a deep learning approach for high similarity date fruit recognition. Journal of Advances in Information Technology,14(6): 1151-1158 [DOI: 10.12720/jait.14.6.1151-1158]
Fingas M F and Brown C E. 1997. Oil spill remote sensors: review,trends and new developments. CONF-970319. [s.n.]
Franke J,Menz G,Oerke E C and Rascher U. 2005. Comparison of multi- and hyperspectral imaging data of leaf rust infected wheat plants//Proceedings of SPIE 5976,Remote Sensing for Agriculture,Ecosystems,and Hydrology VII. Bruges,Belgium: SPIE: #59761D [DOI: 10.1117/12.626531]
Ghamisi P,Yokoya N,Li J,Liao W Z,Liu S C,Plaza J,et al. 2017. Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art. IEEE Geoscience and Remote Sensing Magazine,5(4): 37-78 [DOI: 10.1109/mgrs.2017.2762087]
Gladkikh T Y,Rusakov K D and Grafenkov A V. 2024. Oil pollution detection in aquatic ecosystems using UAVs and multispectral imaging based on deep learning technologies//Proceedings of the 8th International Conference on Information,Control,and Communication Technologies (ICCT). Vladikavkaz,Russian Federation: IEEE: 1-5 [DOI: 10.1109/ICCT62929.2024.10874968]
Gu A and Dao T. 2024. Mamba: linear-time sequence modeling with selective state spaces [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2312.00752.pdf
Hajaj S,El Harti A,Pour A B,Jellouli A,Adiri Z and Hashim M. 2024. A review on hyperspectral imagery application for lithological mapping and mineral prospecting: machine learning techniques and future prospects. Remote Sensing Applications: Society and Environment,35: #101218 [DOI: 10.1016/j.rsase.2024.101218]
He K M,Chen X L,Xie S N,Li Y H,Doll􀅡r P and Girshick R. 2022. Masked autoencoders are scalable vision learners//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans,USA: IEEE: 15979-15988 [DOI: 10.1109/CVPR52688.2022.01553]
He M Y,He J R and Liu H C. 2026. Diversity prompt-guided cross-domain few-shot learning for hyperspectral image classification[J/OL]. Journal of Image and Graphics,1-16
何梦瑶,何进荣,刘寒池. 2026. 多样性提示引导的跨域小样本高光谱图像分类[J/OL]. 中国图象图形学报,1-16 [DOI: 10.11834/jig.250585]
Hinton G,Vinyals O and Dean J. 2015. Distilling the knowledge in a neural network [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/1503.02531.pdf
Hong D F,Han Z,Yao J,Gao L R,Zhang B,Plaza A,et al. 2022. SpectralFormer: rethinking hyperspectral image classification with transformers. IEEE Transactions on Geoscience and Remote Sensing,60: #5518615 [DOI: 10.1109/tgrs.2021.3130716]
Jaderberg M,Simonyan K,Zisserman A and Kavukcuoglu K. 2015. Spatial transformer networks//Proceedings of the 29th International Conference on Neural Information Processing Systems. Montreal,Canada: MIT Press: 2017-2025
Ji R J,Tan K,Wang X,Tang S W,Sun J,Niu C,et al. 2025. PatchOut: a novel patch-free approach based on a transformer-CNN hybrid framework for fine-grained land-cover classification on large-scale airborne hyperspectral images. International Journal of Applied Earth Observation and Geoinformation,138: #104457 [DOI: 10.1016/j.jag.2025.104457]
Ji Y R,Wang C H,Chen J B,Yue A Z,Xi Z H and Chen J S. 2026. Parameter-efficient diffusion model adaptation and spectral consistency learning for controllable multispectral remote sensing image generation[J/OL]. Journal of Image and Graphics,1-16
纪璎芮,王晨昊,陈静波,岳安志,席智浩,陈建胜. 2026. 多光谱遥感图像可控生成的扩散模型参数高效适配与光谱一致性学习[J/OL]. 中国图象图形学报,1-16 [DOI: 10.11834/jig.260089]
Jing L L and Tian Y L. 2021. Self-supervised visual feature learning with deep neural networks: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence,43(11): 4037-4058 [DOI: 10.1109/tpami.2020.2992393]
Justo J A,Garrett J,Langer D D,Henriksen M B,Ionescu R T and Johansen T A. 2023. An open hyperspectral dataset with sea-land-cloud ground-truth from the Hypso-1 satellite//2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). Athens,Greece: IEEE: 1-5 [DOI: 10.1109/WHISPERS61460.2023.10431177]
Kabir S,Rifti I A,Tabib H M S,Rahman M,Sadi S I,Adil H,et al. 2025. SpectraSentinel: LightWeight dual-stream real-time drone detection,tracking and payload identification [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2507.22650.pdf
Kruse F A,Boardman J W and Huntington J F. 2003. Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping. IEEE Transactions on Geoscience and Remote Sensing,41(6): 1388-1400 [DOI: 10.1109/TGRS.2003.812908]
Ledig C,Theis L,Husz􀅡r F,Caballero J,Cunningham A,Acosta A,et al. 2017. Photo-realistic single image super-resolution using a generative adversarial network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,USA: IEEE: 105-114 [DOI: 10.1109/CVPR.2017.19]
Lekhak S,Ientilucci E J,Baur J and Ghosh S. 2026. A UAV-based VNIR hyperspectral benchmark dataset for landmine and UXO detection [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2510.02700.pdf
Li D K,Bhatti U A,Huang M X,Bruzzone L and Li J X. 2026. HyPyraMamba: a pyramid spectral attention and mamba-based architecture for robust hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,64: #5501016 [DOI: 10.1109/tgrs.2025.3650350]
Li G D and Ye M X. 2025. MVNet: hyperspectral remote sensing image classification based on hybrid mamba-transformer vision backbone architecture [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2507.04409.pdf
Li Y,Zhang H K and Shen Q. 2017. Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sensing,9(1): #67 [DOI: 10.3390/rs9010067]
Li Z X,An W,Guo G W,Wang L G,Wang Y Q and Lin Z P. 2025b. SpecDETR: a transformer-based hyperspectral point object detection network. ISPRS Journal of Photogrammetry and Remote Sensing,226: 221-246 [DOI: 10.1016/j.isprsjprs.2025.05.005]
Liu B,Yu X C,Yu A Z,Zhang P Q,Wan G and Wang R R. 2019. Deep few-shot learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,57(4): 2290-2304 [DOI: 10.1109/TGRS.2018.2872830]
Liu B,Yu X C,Zhang P Q,Tan X,Yu A Z and Xue Z X. 2017. A semi-supervised convolutional neural network for hyperspectral image classification. Remote Sensing Letters,8(9): 839-848 [DOI: 10.1080/2150704X.2017.1331053]
Liu P F,Bai H Y,Xu T F,Wang J H,Chen H and Li J N. 2025a. Hyperspectral remote sensing images salient object detection: the first benchmark dataset and baseline. IEEE Transactions on Geoscience and Remote Sensing,63: #5511014 [DOI: 10.1109/TGRS.2025.3558189]
Liu T,Qi Y,Yang F,Yi X Y,Guo S L,Wu P Y,et al. 2025b. Early detection of rice blast using UAV hyperspectral imagery and multi-scale integrator selection attention transformer network (MS-STNet). Computers and Electronics in Agriculture,231: #110007 [DOI: 10.1016/j.compag.2025.110007]
Liu Y,Pang C,Zhan Z Q,Zhang X M and Yang X. 2021. Building change detection for remote sensing images using a dual-task constrained deep Siamese convolutional network model. IEEE Geoscience and Remote Sensing Letters,18(5): 811-815 [DOI: 10.1109/LGRS.2020.2988032]
Liu Y,Zhang Y J and Zhang J H. 2025c. Lightweight multi-head MambaOut with CosTaylorFormer for hyperspectral image classification. Remote Sensing,17(11): #1864 [DOI: 10.3390/rs17111864]
Loncan L,de Almeida L B,Bioucas-Dias J M,Briottet X,Chanussot J,Dobigeon N,et al. 2015. Hyperspectral pansharpening: a review. IEEE Geoscience and Remote Sensing Magazine,3(3): 27-46 [DOI: 10.1109/MGRS.2015.2440094]
Lu F Y,Zhang B M,Hou Y F,Xiong X,Dong C R,Lu W B,et al. 2025. A spatiotemporal attention-guided graph neural network for precise hyperspectral estimation of corn nitrogen content. Agronomy,15(5): #1041 [DOI: 10.3390/agronomy15051041]
Luo F L,Liu Y,Gong X W,Nan Z X and Guo T. 2024. EMVCC: enhanced multi-view contrastive clustering for hyperspectral images//Proceedings of the 32nd ACM International Conference on Multimedia. Melbourne,Australia: ACM: 6288-6296 [DOI: 10.1145/3664647.3681600]
Luo S,Qian Y R,Bai L,Fan Y Y,Wang Y X and Kong W Q. 2025. Deep learning-based hyperspectral and multispectral fusion techniques: review,optimization,and perspectives. Information Fusion,124: #103291 [DOI: 10.1016/j.inffus.2025.103291]
Lyu G H,Gao X,Chi Q,Zhao G X,Dong A M and Li W. 2025. SSFSL: self-supervised and few-shot learning for cross-domain hyperspectral image classification//Proceedings of 2025 ICASSP IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Hyderabad,India: IEEE: 1-5 [DOI: 10.1109/ICASSP49660.2025.10889995]
Ma J Y,Yu W,Liang P W,Li C and Jiang J J. 2019. FusionGAN: a generative adversarial network for infrared and visible image fusion. Information Fusion,48: 11-26 [DOI: 10.1016/j.inffus.2018.09.004]
Maes W H and Steppe K. 2019. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture. Trends in Plant Science,24(2): 152-164 [DOI: 10.1016/j.tplants.2018.11.007]
Makki I,Younes R,Francis C,Bianchi T and Zucchetti M. 2017. A survey of landmine detection using hyperspectral imaging. ISPRS Journal of Photogrammetry and Remote Sensing,124: 40-53 [DOI: 10.1016/j.isprsjprs.2016.12.009]
Manolakis D,Golowich S and DiPietro R S. 2014. Long-wave infrared hyperspectral remote sensing of chemical clouds: a focus on signal processing approaches. IEEE Signal Processing Magazine,31(4): 120-141 [DOI: 10.1109/msp.2013.2294804]
Martin-Gallausiaux C,Marinelli L,Blottière H M,Larraufie P and Lapaque N. 2021. SCFA: mechanisms and functional importance in the gut. Proceedings of the Nutrition Society,80(1): 37-49 [DOI: 10.1017/S0029665120006916]
Mazzia V,Khaliq A,Salvetti F and Chiaberge M. 2020. Real-time apple detection system using embedded systems with hardware accelerators: an edge AI application. IEEE Access,8: 9102-9114 [DOI: 10.1109/ACCESS.2020.2964608]
Melgani F and Bruzzone L. 2004. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on Geoscience and Remote Sensing,42(8): 1778-1790 [DOI: 10.1109/TGRS.2004.831865]
Meng G,Cai Z N,Tu J Y,Wang Y Y,Li C X,Huang Y,et al. 2025. PCMamba: physics-informed cross-modal state space model for dual-camera compressive hyperspectral imaging [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2505.16373.pdf
Osco L P,Arruda M D S D,Marcato Junior J,da Silva N B,Ramos A P M,Moryia É A S,et al. 2020. A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing,160: 97-106 [DOI: 10.1016/j.isprsjprs.2019.12.010]
Paeedeh N,Pratama M,Shiddiqi A,Cao Z H,Prasad M and Jatmiko W. 2026. Cross-domain few-shot learning for hyperspectral image classification based on Mixup foundation model [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2601.22581.pdf
Pant A,Baniya A A,Lee T K and Aryal S. 2025. Hyperspectral anomaly detection methods: a survey and comparative study [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2507.05730.pdf
Peng X,Wang P T,Zhou K,Yan Z P,Zhong X G and Zhao C. 2025. Bridge defect detection using small sample data with deep learning and hyperspectral imaging. Automation in Construction,170: #105900 [doi: 10.1016/j.autcon.2024.105900]
Picollo M,Cucci C,Casini A and Stefani L. 2020. Hyper-spectral imaging technique in the cultural heritage field: new possible scenarios. Sensors,20(10): #2843 [DOI: 10.3390/s20102843]
Pohl C and van Genderen J L. 1998. Review article multisensor image fusion in remote sensing: concepts,methods and applications. International Journal of Remote Sensing,19(5): 823-854 [DOI: 10.1080/014311698215748]
Qiu Y H,Bai S Y,Xu T F,Liu P F,Qin H L and Li J N. 2025. HSOD-BIT-V2: a challenging benchmark for hyperspectral salient object detection//Proceedings of the 39th AAAI Conference on Artificial Intelligence. Philadelphia,USA: AAAI Press: 6630-6638 [DOI: 10.1609/aaai.v39i6.32711]
Qu Y,Qi H R and Kwan C. 2018. Unsupervised sparse Dirichlet-net for hyperspectral image super-resolution//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA: IEEE: 2511-2520 [DOI: 10.1109/CVPR.2018.00266]
Rasti B,Hong D F,Hang R L,Ghamisi P,Kang X D,Chanussot J,et al. 2020. Feature extraction for hyperspectral imagery: the evolution from shallow to deep: overview and toolbox. IEEE Geoscience and Remote Sensing Magazine,8(4): 60-88 [DOI: 10.1109/MGRS.2020.2979764]
Ren S Q,He K M,Girshick R and Sun J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence,39(6): 1137-1149 [DOI: 10.1109/tpami.2016.2577031]
Roy S K,Krishna G,Dubey S R and Chaudhuri B B. 2020. HybridSN: exploring 3-D—2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters,17(2): 277-281 [DOI: 10.1109/lgrs.2019.2918719]
Sankararao A U G,Rajalakshmi P and Choudhary S. 2024. UC-HSI: UAV-based crop hyperspectral imaging datasets and machine learning benchmark results. IEEE Geoscience and Remote Sensing Letters,21: #5508005 [DOI: 10.1109/LGRS.2024.3431644]
Shimoni M,Haelterman R and Perneel C. 2019. Hyperspectral imaging for military and security applications: combining myriad processing and sensing techniques. IEEE Geoscience and Remote Sensing Magazine,7(2): 101-117 [DOI: 10.1109/MGRS.2019.2902525]
Shrestha M,Scholl V,Sampath A,Irwin J,Kropuenske T,Adams J,et al. 2025. Absolute radiometric calibration evaluation of uncrewed aerial system (UAS) headwall and MicaSense sensors and improving data quality using the empirical line method. Remote Sensing,17(22): #3738 [DOI: 10.3390/rs17223738]
Sishodia R P,Ray R L and Singh S K. 2020. Applications of remote sensing in precision agriculture: a review. Remote Sensing,12(19): #3136 [DOI: 10.3390/rs12193136]
Su H J,Wu Z Y,Zhang H H and Du Q. 2022. Hyperspectral anomaly detection: a survey. IEEE Geoscience and Remote Sensing Magazine,10(1): 64-90 [DOI: 10.1109/MGRS.2021.3105440]
Tan M X and Le Q V. 2019. EfficientNet: rethinking model scaling for convolutional neural networks//Proceedings of the 36th International Conference on Machine Learning. Long Beach,USA: PMLR: 6105-6114
Tang S M and Chen Y L. 2026. Detecting citrus from multispectral remote sensing images using an improved YOLOv8 model. Transactions of the Chinese Society of Agricultural Engineering,42(2): 205-213
唐淑铭,陈优良. 2026. 基于改进YOLOv8的多光谱遥感影像脐橙树检测方法. 农业工程学报,42(2): 205-213 [DOI: 10.11975/j.issn.1002-6819.202507057]
Tapete D and Cigna F. 2019. Detection of archaeological looting from space: methods,achievements and challenges. Remote Sensing,11(20): #2389 [DOI: 10.3390/rs11202389]
Torresan C,Berton A,Carotenuto F,Di Gennaro S F,Gioli B,Matese A,et al. 2017. Forestry applications of UAVs in Europe: a review. International Journal of Remote Sensing,38(8/10): 2427-2447 [DOI: 10.1080/01431161.2016.1252477]
Toutin T. 2004. Review article: geometric processing of remote sensing images: models,algorithms and methods. International Journal of Remote Sensing,25(10): 1893-1924 [DOI: 10.1080/0143116031000101611]
Ulyanov D,Vedaldi A and Lempitsky V. 2018. Deep image prior//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City,USA: IEEE: 9446-9454 [DOI: 10.1109/CVPR.2018.00984]
Vaddi R,Phaneendra Kumar B L N,Mitra S,Mitra S,Bruzzone L and Roy S K. 2025. From traditional to foundation models: a survey for land use and land cover hyperspectral image classification. WIREs Data Mining and Knowledge Discovery,15(4): #70049 [DOI: 10.1002/widm.70049]
van der Meer F D,van der Werff H M A,van Ruitenbeek F J A,Hecker C A,Bakker W H,Noomen M F,et al. 2012. Multi- and hyperspectral geologic remote sensing: a review. International Journal of Applied Earth Observation and Geoinformation,14(1): 112-128 [DOI: 10.1016/j.jag.2011.08.002]
Vermote E F,Tanré D,Deuze J L,Herman M and Morcette J J. 1997. Second simulation of the satellite signal in the solar spectrum,6S: an overview. IEEE Transactions on Geoscience and Remote Sensing,35(3): 675-686 [DOI: 10.1109/36.581987]
Wan D H,Lu R S,Fang Y,Lang X L,Shu S B,Chen J J,et al. 2025. YOLOv11-RGBT: towards a comprehensive single-stage multispectral object detection framework [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2506.14696.pdf
Wang D,Hu M Q,Jin Y,Miao Y C,Yang J Q,Xu Y C,et al. 2025. HyperSIGMA: hyperspectral intelligence comprehension foundation model. IEEE Transactions on Pattern Analysis and Machine Intelligence,47(8): 6427-6444 [DOI: 10.1109/TPAMI.2025.3557581]
Wang X H,Zhao K Y,Zhao X Y and Li S Y. 2023. GTMSiam: gated transmitting-based multiscale Siamese network for hyperspectral image change detection. IEEE Geoscience and Remote Sensing Letters,20: #5511805 [DOI: 10.1109/LGRS.2023.3329348]
Wang Y,Wen M,Zhang H L,Sun J Y,Yang Q,Zhang Z M,et al. 2024. HSIMAE: a unified masked autoencoder with large-scale pretraining for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,17: 14064-14079 [DOI: 10.1109/JSTARS.2024.3432743]
Xie Z Y,Lyu L,Gao H M,Xu S F and Xie H H. 2025. Dual-feature attention hybrid GCN mamba network for joint hyperspectral and LiDAR classification. IEEE Transactions on Geoscience and Remote Sensing,63: #5406514 [DOI: 10.1109/TGRS.2025.3605373]
Xu Y C,Wang D,Zhang L F and Zhang L P. 2025. Dual selective fusion transformer network for hyperspectral image classification. Neural Networks,187: #107311 [DOI: 10.1016/j.neunet.2025.107311]
Xue J Z,Yu F M and Liu Y. 2026. Hyperspectral and multispectral image fusion via sparse reconstruction and cross-guidance. Journal of Image and Graphics,1-14
薛吉则,俞凤梅,刘颖. 2026. 稀疏重建与交叉引导的高光谱与多光谱图像融合. 中国图象图形学报,1-14 [DOI: 10.11834/jig.250618]
Yang J F,Fu X Y,Hu Y W,Huang Y,Ding X H and Paisley J. 2017. PanNet: a deep network architecture for pan-sharpening//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice,Italy: IEEE: 1753-1761 [DOI: 10.1109/ICCV.2017.193]
Yel S G and Tunc Gormus E. 2023. Exploiting hyperspectral and multispectral images in the detection of tree species: a review. Frontiers in Remote Sensing,4: #1136289 [DOI: 10.3389/frsen.2023.1136289]
Yokoya N,Grohnfeldt C and Chanussot J. 2017. Hyperspectral and multispectral data fusion: a comparative review of the recent literature. IEEE Geoscience and Remote Sensing Magazine,5(2): 29-56 [DOI: 10.1109/MGRS.2016.2637824]
Yokoya N,Yairi T and Iwasaki A. 2012. Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion. IEEE Transactions on Geoscience and Remote Sensing,50(2): 528-537 [DOI: 10.1109/tgrs.2011.2161320]
Yu B H,Liang J X,Wang Z F,Fan B,Subpa-asa A,Shi B X,et al. 2025. Active hyperspectral imaging using an event camera//Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville,USA: IEEE: 929-939 [DOI: 10.1109/CVPR52734.2025.00095]
Yu C Y,Gong B Y,Song M P,Zhao E Y and Chang C I. 2022. Multiview calibrated prototype learning for few-shot hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,60: #5544713 [DOI: 10.1109/TGRS.2022.3225947]
Yu T,Li L,Luo X and Li Q. 2023. ReM-YOLO: a new lightweight vehicle parts target detection algorithm//Proceedings of 2023 International Conference on Pattern Recognition,Machine Vision and Intelligent Algorithms (PRMVIA). Beihai,China: IEEE: 90-97 [DOI: 10.1109/PRMVIA58252.2023.00022]
Yuan H B,Zhu J J,Wang Q F,Cheng M and Cai Z J. 2022. An improved DeepLab v3+ deep learning network applied to the segmentation of grape leaf black rot spots. Frontiers in Plant Science,13: #795410 [DOI: 10.3389/fpls.2022.795410]
Yuan Q Q,Zhang Q,Li J,Shen H F and Zhang L P. 2019. Hyperspectral image denoising employing a spatial-spectral deep residual convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing,57(2): 1205-1218 [DOI: 10.1109/TGRS.2018.2865197]
Zakaria Sellam A,Abdeladhim Zidi F,Eddine Bekhouche S,Houhou I,Tliba M,Distante C,et al. 2026. VP-Hype: a hybrid mamba-transformer framework with visual-textual prompting for hyperspectral image classification [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2603.01174.pdf
Zhang B J,Wang L,Yao Q W,Li K Y and Tan Q Y. 2026. SG-YOLO: a multispectral small-object detector for UAV imagery based on YOLO. Remote Sensing,18(7): #1003 [DOI: 10.3390/rs18071003]
Zhang H R and Xu X. 2024. A lightweight hybrid CNN-mamba network for hyperspectral image classification//Proceedings of the 2nd Asia Symposium on Image and Graphics. Sanya,China: ACM: 73-78 [DOI: 10.1145/3718441.3718452]
Zhang K,Zuo W M,Chen Y J,Meng D Y and Zhang L. 2017. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing,26(7): 3142-3155 [DOI: 10.1109/TIP.2017.2662206]
Zhang Q,Zheng Y M,Yuan Q Q,Song M P,Yu H Y and Xiao Y. 2024. Hyperspectral image denoising: from model-driven,data-driven,to model-data-driven. IEEE Transactions on Neural Networks and Learning Systems,35(10): 13143-13163 [DOI: 10.1109/TNNLS.2023.3278866]
Zhang W H,Jiang C Z,Dong M J,Gui J,Dong L,Gui Z P,et al. 2025a. Revisiting adversarial training under hyperspectral image [EB/OL]. [2026-04-01]. https://arxiv.org/pdf/2510.01014.pdf
Zhang Z Q,Wang Y,Gao D H,Li H Y and Shi G M. 2025b. Spectral-spatial mamba adversarial defense network for hyperspectral image classification. International Journal of Digital Earth,18(1): #2520480 [DOI: 10.1080/17538947.2025.2520480]
Zhao X F,Zhang H,Li C X,Wang K H and Zhang Z L. 2025. DVIF-Net: a small-target detection network for UAV aerial images based on visible and infrared fusion. Remote Sensing,17(20): #3411 [DOI: 10.3390/rs17203411]
Zhou Q Z,Guo Q,Wang H R and Li A. 2024. Two-discriminators-deep residual GAN hyperspectral image pan-sharpening. Journal of Image and Graphics,29(7): 2046-2062
周庆泽,郭擎,王海荣,李安. 2024. 双判别器深度残差GAN高光谱图像融合. 中国图象图形学报,29(7): 2046-2062 [DOI: 10.11834/jig.220932]
Zhu M H,Wang H,Meng Y B,Xu S J,Lin Y H,Shan Z,et al. 2025. Self-supervised mamba for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing,63: #5531312 [DOI: 10.1109/TGRS.2025.3622597]
Zhu S Y,Song Y H,Zhang Y and Zhang Y L. 2023. ECFNet: a Siamese network with fewer FPs and fewer FNs for change detection of remote-sensing images. IEEE Geoscience and Remote Sensing Letters,20: #6001005 [DOI: 10.1109/LGRS.2023.3238553]
Zhu X X,Tuia D,Mou L C,Xia G S,Zhang L P,Xu F,et al. 2017. Deep learning in remote sensing: a comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine,5(4): 8-36 [DOI: 10.1109/MGRS.2017.2762307]
2026年第31卷第9期
PDF下载
20
8
引用本文
BibTeX
文章信息
doi: 10.11834/jig.260210
  • 接收时间:2026-04-16
  • 首发时间:2026-10-30
  • 出版时间:2026-09-16
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2026-04-16
  • 修回日期:2026-06-05
基金
National Natural Science Foundation of China (62372379,62472359)
国家自然科学基金项目 (62372379,62472359)
作者信息
    1 西北工业大学国家卓越工程师学院,西安 710100
    2 宇航智能控制技术全国重点实验室,北京 100854
    3 北京航天自动控制研究所,北京 100854
    4 曲靖健康医学院,曲靖 655100
    5 西北工业大学计算机学院,西安 710100

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.260210
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏