Article(id=1322963049459622284, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322962941087195876, articleNumber=null, orderNo=null, doi=10.11834/jig.250491, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1759420800000, receivedDateStr=2025-10-03, revisedDate=1772380800000, revisedDateStr=2026-03-02, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348570455, onlineDateStr=2026-10-30, pubDate=1792080000000, pubDateStr=2026-10-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348570455, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348570455, creator=13701087609, updateTime=1793348570455, updator=13701087609, issue=Issue{id=1322962941087195876, tenantId=1146029695717560320, journalId=1249024232475115590, year='2026', volume='31', issue='10', pageStart='3441', pageEnd='3818', issueExtLink='null', onlineDate='null', pubDate='1792080000000', pubDateStr='2026-10-16', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1793348544618, creator='13701087609', updateTime=1793348641113, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1322963345913021357, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322962941087195876, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1322963345913021358, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322962941087195876, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=3653, endPage=3670, ext={EN=ArticleExt(id=1322963049698697613, articleId=1322963049459622284, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=Small-object detection network for wide-field surveillance video: SOD-YOLO, columnId=1249044019595125147, journalTitle=Journal of Image and Graphics, columnName=Image Analysis and Recognition, runingTitle=null, highlight=null, articleAbstract=
Objective Small-object detection in large-field-of-view (FOV) surveillance videos remains a persistent challenge in real-world applications such as construction-site safety monitoring,traffic supervision in highway service areas,and public-space management on university campuses. Compared with conventional close-range datasets,targets in large-FOV imagery are often extremely small and are heavily affected by background clutter,illumination variation,compression noise,motion blur,and frequent occlusion. Therefore,detectors trained on generic benchmarks typically face three intertwined bottlenecks: 1) scarce and costly annotations for tiny objects across diverse surveillance scenes; 2) weak and ambiguous visual features caused by limited pixel coverage and low signal-to-noise ratio,which makes tiny targets difficult to distinguish from the background; and 3) inaccurate localization,where even a deviation of a few pixels can substantially reduce intersection over union (IoU),thereby harming high-precision metrics and downstream tracking or analysis. To address these issues in a unified manner,this study proposes SOD-YOLO,a small-object-oriented detector designed for low-resolution,large-FOV surveillance videos. The primary goal is to enhance supervision signals,strengthen tiny-feature representation,and improve high-precision localization simultaneously,thereby delivering reliable performance under practical surveillance constraints.
Method SOD-YOLO follows a data-feature-localization co-design philosophy and introduces improvements in three aspects. 1) Virtual-real fusion sample generation. To alleviate the scarcity of real annotations and increase the diversity of tiny-object appearances and backgrounds,we propose a cost-effective data-generation strategy that combines SAM2 (segment anything model v2) semantic guidance with unreal engine (UE) virtual simulation. SAM2 is used to obtain fine-grained object masks and semantic cues,enabling high-quality object cutout,composition,and accurate label transfer for small objects. UE is used to generate controllable virtual surveillance scenes with precise ground-truth annotations,in which camera viewpoints,object-scale distributions,lighting conditions,and scene layouts are configured to mimic real surveillance patterns. These synthetic data are mixed with real samples to expand the training distribution,improving robustness to background variation and rare target configurations while keeping labeling costs manageable. 2) Tiny-object feature enhancement. Because tiny targets provide weak cues that are easily overwhelmed in large-FOV frames,we design a feature-enhancement mechanism with three components. First,video differential preprocessing explicitly highlights subtle foreground changes and suppresses irrelevant static textures. Second,strengthened multi-scale feature fusion better integrates fine-grained spatial detail from shallow layers with semantic context from deeper layers,allowing the network to preserve small-object signals while retaining discriminative context. Third,bilevel routing attention (BRA) is incorporated to allocate attention adaptively to informative regions and improve the model’s ability to perceive and distinguish tiny targets under clutter and occlusion. 3) Localization-oriented optimization. To address the strong localization sensitivity of small objects,SOD-YOLO adopts a decoupled head that separates classification and regression learning,reducing task conflict and stabilizing optimization when supervision is weak. In addition,we propose an α-CIoU loss to improve regression precision and encourage better alignment at higher IoU thresholds,directly targeting the common failure mode of loose or shifted bounding boxes for tiny objects. Collectively,these designs form an end-to-end detector that improves learning from limited data,enhances tiny-feature representation,and refines bounding-box regression.
Result Extensive experiments were conducted on three real-scene large-FOV surveillance datasets: construction site,highway service area,and university campus,covering multi-category detection of pedestrians,e-bikes,cars,trucks,and buses,as well as extremely small targets under complex backgrounds. Evaluation followed COCO-style metrics,with particular emphasis on high-IoU and small-object performance. On the construction-site dataset,SOD-YOLO achieved the best localization-sensitive performance,with an AP75 of 13.5% and an AP50s of 53.9%,indicating superior high-precision bounding-box regression and sensitivity to small targets in cluttered scenes. On the highway service-area dataset,which is characterized by dense traffic and large intra-class variation,SOD-YOLO reached the best overall AP of 42.6% and an AP75 of 29.5%,demonstrating robust general performance and high-IoU accuracy under complex multi-class conditions. On the especially challenging university-campus dataset,where the smallest objects may occupy only about 0.007 5% of image pixels and minor offsets severely degrade IoU,SOD-YOLO clearly outperformed the YOLOv7 baseline,improving AP,AP75,and AP50s by approximately 4.9%,2.5%,and 5.0%,respectively. To further verify generalization,we evaluated SOD-YOLO on the public VT-TOD visible benchmark under the official split. The model achieved leading performance,with a precision of 61.4%,an AP50:95 of 52.3%,an APs of 63.5%,and an APm of 58.2%,outperforming representative methods such as QueryDet,YOLOC,and Drone-YOLO. Ablation studies confirmed that every proposed component contributes positively: differential preprocessing produced the most notable gain by enhancing foreground saliency; multi-scale fusion and BRA provided additional gains by strengthening discriminative representations; and the decoupled head together with α-CIoU consistently improved high-IoU localization quality. Experiments on virtual-real mixing ratios showed that a balanced fusion strategy best exploits synthetic diversity while preserving realism,whereas overreliance on synthetic data can reduce generalization because of domain gaps.
Conclusion This study proposes SOD-YOLO as an effective and reliable solution for small-object detection in low-resolution,large-FOV surveillance videos. By integrating virtual-real fusion data generation,tiny-feature enhancement,and localization-oriented optimization,SOD-YOLO improves both robustness and precision across diverse real surveillance scenarios and a public benchmark,particularly under high-IoU and small-object settings. The proposed framework provides a practical pathway toward deploying accurate small-object detectors in real monitoring systems where annotation scarcity,weak features,and localization sensitivity are critical constraints.
, authors=Jun Wu1
, 2, Guangzhen Cai1, Hexuan Chu1, Gang Xu1, Xuemei Zhao1
, 3, Heng Yin1
, *, authorsList=Jun Wu, Guangzhen Cai, Hexuan Chu, Gang Xu, Xuemei Zhao, Heng Yin, authorCompany=null, correspAuthors=Heng Yin, 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=1322963053830087078, articleId=1322963049459622284, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=用于大视场监控视频的小目标检测网络SOD-YOLO, columnId=1249044019838394781, journalTitle=中国图象图形学报, columnName=图像分析和识别, runingTitle=null, highlight=null, articleAbstract=
目的 针对大视场监控视频中小目标检测存在的样本稀缺、特征微弱与定位不准等难题,提出一种用于大视场监控视频的小目标检测网络SOD-YOLO(small object detection-you only look once)。
方法 该方法从3个层面系统性地进行改进:1)提出结合SAM2(segment anything model 2 )语义指导与UE虚拟仿真的虚实融合样本生成策略,以低成本获取大量高质量标注数据;2)设计包含视频差分预处理、多尺度特征融合及双层路由注意力的特征增强机制,以提升模型对微小特征的感知与分辨能力;3)采用解耦头结构并创新-CIoU(alpha-complete intersection over union)损失函数,以优化小目标边界框的回归精度。
结果 在建设工地、高速公路服务区及大学校园3个真实场景数据集上的实验结果表明,SOD-YOLO的综合性能显著优于当前主流模型,在建筑工地场景取得最高AP75(13.5%)与AP50s(53.9%);在高速公路服务区场景获得最优AP(42.6%)与AP75(29.5%);尤其在极具挑战的大学校园场景(小目标像素占比约0.007 5%),其AP、AP75与AP50s相较基准模型YOLOv7分别提升了4.9%、2.5%与5.0%。
结论 本研究为解决低分辨率监控视频下的小目标检测问题提供了一套有效且可靠的技术方案。
, authors=吴军1
, 2, 蔡广震1, 楚和轩1, 徐刚1, 赵雪梅1
, 3, 尹恒1
, *, authorsList=吴军, 蔡广震, 楚和轩, 徐刚, 赵雪梅, 尹恒, authorCompany=null, correspAuthors=尹恒, authorNote=
, correspAuthorsNote=
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=veba2B9hwsXX5bk9yXq+Fg==, magXml=3+12ORAKLdfe/PNbChbjpg==, pdfUrl=null, pdf=s6pDtn59UxtsrNZMJ5nljg==, pdfFileSize=11120536, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=QWETjRFfeZoY/eD7DuugOA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=KUVabBQlpjh5/FMCv7KJfQ==, mapNumber=null, fund=null)}, authors=[Author(id=1322963055935627697, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wujun@guet.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963056032096692, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963055935627697, language=EN, stringName=Jun Wu, firstName=Jun, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1
, 2, address=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China
2 Guangxi Academy of Sciences,Nanning 530000,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963056120177077, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963055935627697, language=CN, stringName=吴军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1
, 2, address=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004
2 广西科学院,南宁 530000, bio={"content":"
吴军,男,教授,博士生导师,主要研究方向为测绘遥感、视频安防、计算机视觉及嵌入式系统构建。E-mail: wujun@guet.edu.cn
"}, bioImg=null, bioContent=
吴军,男,教授,博士生导师,主要研究方向为测绘遥感、视频安防、计算机视觉及嵌入式系统构建。E-mail: wujun@guet.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)]), AuthorCompany(id=1322963054165631402, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=2, ext=[AuthorCompanyExt(id=1322963054174020011, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054165631402, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2 Guangxi Academy of Sciences,Nanning 530000,China), AuthorCompanyExt(id=1322963054186602924, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054165631402, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2 广西科学院,南宁 530000)])]), Author(id=1322963056195674551, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=cgz@mails.guet.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963056296337849, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056195674551, language=EN, stringName=Guangzhen Cai, firstName=Guangzhen, middleName=null, lastName=Cai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963056405389754, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056195674551, language=CN, stringName=蔡广震, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004, bio={"content":"
蔡广震,男,硕士研究生,主要研究方向为人工智能和视频目标检测。E-mail: cgz@mails.guet.edu.cn
"}, bioImg=null, bioContent=
蔡广震,男,硕士研究生,主要研究方向为人工智能和视频目标检测。E-mail: cgz@mails.guet.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)])]), Author(id=1322963056485081532, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chuhexuan03@mails.guet.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963056577356222, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056485081532, language=EN, stringName=Hexuan Chu, firstName=Hexuan, middleName=null, lastName=Chu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963056644465087, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056485081532, language=CN, stringName=楚和轩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004, bio={"content":"
楚和轩,男,硕士研究生,主要研究方向为视频目标检测。E-mail: chuhexuan03@mails.guet.edu.cn
"}, bioImg=null, bioContent=
楚和轩,男,硕士研究生,主要研究方向为视频目标检测。E-mail: chuhexuan03@mails.guet.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)])]), Author(id=1322963056732545473, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xugang@nimte.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963056816431555, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056732545473, language=EN, stringName=Gang Xu, firstName=Gang, middleName=null, lastName=Xu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963056891929028, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056732545473, language=CN, stringName=徐刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004, bio={"content":"
徐刚,男,博士研究生,主要研究方向为计算机视觉。E-mail: xugang@nimte.ac.cn
"}, bioImg=null, bioContent=
徐刚,男,博士研究生,主要研究方向为计算机视觉。E-mail: xugang@nimte.ac.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)])]), Author(id=1322963056975815110, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaoxm@guet.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963057068089801, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056975815110, language=EN, stringName=Xuemei Zhao, firstName=Xuemei, middleName=null, lastName=Zhao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1
, 3, address=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China
3 Key Laboratory of Intelligent Integrated Automation, Guangxi Higher Education Institutions,Guilin 541004,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963057131004362, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963056975815110, language=CN, stringName=赵雪梅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1
, 3, address=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004
3 智能综合自动化广西高校重点实验室,桂林 541004, bio={"content":"
赵雪梅,女,教授,主要研究方向为测绘遥感和人工智能。E-mail:zhaoxm@guet.edu.cn
"}, bioImg=null, bioContent=
赵雪梅,女,教授,主要研究方向为测绘遥感和人工智能。E-mail:zhaoxm@guet.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)]), AuthorCompany(id=1322963054266294701, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=3, ext=[AuthorCompanyExt(id=1322963054270489006, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054266294701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3 Key Laboratory of Intelligent Integrated Automation, Guangxi Higher Education Institutions,Guilin 541004,China), AuthorCompanyExt(id=1322963054278877615, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054266294701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3 智能综合自动化广西高校重点实验室,桂林 541004)])]), Author(id=1322963057227473356, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yinh@guet.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322963057319748046, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963057227473356, language=EN, stringName=Heng Yin, firstName=Heng, middleName=null, lastName=Yin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1
, *, address=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963057416217039, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, authorId=1322963057227473356, language=CN, stringName=尹恒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1
, *, address=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004, bio={"content":"
尹恒,通信作者,男,博士后,主要研究方向为计算机视觉和多源遥感数据智能处理与分析。E-mail: yinh@guet.edu.cn
"}, bioImg=null, bioContent=
尹恒,通信作者,男,博士后,主要研究方向为计算机视觉和多源遥感数据智能处理与分析。E-mail: yinh@guet.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)])])], keywords=[Keyword(id=1322963057529463248, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, orderNo=1, keyword=video surveillance), Keyword(id=1322963057600766417, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, orderNo=2, keyword=convolutional neural network (CNN)), Keyword(id=1322963057676263890, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, orderNo=3, keyword=small object detection), Keyword(id=1322963057739178451, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, orderNo=4, keyword=small object bounding-box localization), Keyword(id=1322963057797898708, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, orderNo=5, keyword=sample augmentation), Keyword(id=1322963057869201877, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, orderNo=1, keyword=视频监控), Keyword(id=1322963057948893654, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, orderNo=2, keyword=卷积神经网络 (CNN)), Keyword(id=1322963058024391127, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, orderNo=3, keyword=小目标检测), Keyword(id=1322963058095694296, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, orderNo=4, keyword=小目标边界框定位), Keyword(id=1322963058179580377, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, orderNo=5, keyword=样本增广)], refs=[Reference(id=1322963064995324418, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=210, pageEnd=226, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Bai Y C, Zhang Y Q, Ding M L, Ghanem B, journalName=null, refType=null, unstructuredReference=
Bai Y C,
Zhang Y Q,
Ding M L and
Ghanem B.
2018. SOD-MTGAN: small object detection via multi-task generative adversarial network//Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich,Germany: Springer: 210-226 [DOI:
10.1007/978-3-030-01261-8_13], articleTitle=SOD-MTGAN: small object detection via multi-task generative adversarial network, refAbstract=null), Reference(id=1322963065091793411, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=3759, pageEnd=3768, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Bryan B, Gong Y, Zhang Y Z, Poellabauer C, journalName=null, refType=null, unstructuredReference=
Bryan B,
Gong Y,
Zhang Y Z and
Poellabauer C.
2019. Second-order non-local attention networks for person re-identification//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul,Korea(South): IEEE: 3759-3768 [DOI:
10.1109/ICCV.2019.00386], articleTitle=Second-order non-local attention networks for person re-identification, refAbstract=null), Reference(id=1322963065196651012, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=6154, pageEnd=6162, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Cai Z W, Vasconcelos N, journalName=null, refType=null, unstructuredReference=
Cai Z W and
Vasconcelos N.
2018. Cascade R-CNN: delving into high quality object detection//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City,USA: IEEE: 6154-6162 [DOI:
10.1109/CVPR.2018.00644], articleTitle=Cascade R-CNN: delving into high quality object detection, refAbstract=null), Reference(id=1322963065301508613, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2025, volume=34, issue=null, pageStart=6813, pageEnd=6822, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Cao M, Ikehata S, Aizawa K, journalName=IEEE Transactions on Image Processing, refType=null, unstructuredReference=
Cao M,
Ikehata S and
Aizawa K.
2025. Field-of-view IoU for object detection in 360° images.
IEEE Transactions on Image Processing,
34: 6813-6822 [DOI:
10.1109/TIP.2023.3296013], articleTitle=Field-of-view IoU for object detection in 360° images, refAbstract=null), Reference(id=1322963065418949126, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=62, issue=null, pageStart=null, pageEnd=5007613, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Chen T X, Ye Z, Tan Z T, Gong T, Wu Y, Chu Q, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=
Chen T X,
Ye Z,
Tan Z T,
Gong T,
Wu Y,
Chu Q,
et al.
2024. MiM-ISTD: Mamba-in-Mamba for efficient infrared small-target detection.
IEEE Transactions on Geoscience and Remote Sensing,
62: #5007613 [DOI:
10.1109/TGRS.2024.3485721], articleTitle=MiM-ISTD: Mamba-in-Mamba for efficient infrared small-target detection, refAbstract=null), Reference(id=1322963065498640903, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2022, volume=24, issue=null, pageStart=1968, pageEnd=1979, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Deng C F, Wang M M, Liu L, Liu Y, Jiang Y L, journalName=IEEE Transactions on Multimedia, refType=null, unstructuredReference=
Deng C F,
Wang M M,
Liu L,
Liu Y and
Jiang Y L.
2022. Extended feature pyramid network for small object detection.
IEEE Transactions on Multimedia,
24: 1968-1979 [DOI:
10.1109/TMM.2021.3074273], articleTitle=Extended feature pyramid network for small object detection, refAbstract=null), Reference(id=1322963065603498504, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=82, issue=6, pageStart=9243, pageEnd=9275, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=Diwan T, Anirudh G, Tembhurne J V, journalName=Multimedia Tools and Applications, refType=null, unstructuredReference=
Diwan T,
Anirudh G and
Tembhurne J V.
2023. Object detection using YOLO: challenges,architectural successors,datasets and applications.
Multimedia Tools and Applications,
82(6): 9243-9275 [DOI:
10.1007/s11042-022-13644-y], articleTitle=Object detection using YOLO: challenges,architectural successors,datasets and applications, refAbstract=null), Reference(id=1322963065746104841, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=16, pageEnd=16, url=null, language=null, rfNumber=null, rfOrder=7, authorNames=Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X H, Unterthiner T, journalName=An image is worth, refType=null, unstructuredReference=
Dosovitskiy A,
Beyer L,
Kolesnikov A,
Weissenborn D,
Zhai X H,
Unterthiner T,
et al.
2021.
An image is worth 16 × 16 words: transformers for image recognition at scale//Proceedings of 2021 International Conference on Learning Representations. Vienna,Austria: OpenReview.net, articleTitle=words: transformers for image recognition at scale, refAbstract=null), Reference(id=1322963065855156746, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=177, issue=null, pageStart=null, pageEnd=111221, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Hao X Y, Luo S J, Chen M Y, He C H, Wang T, Wu H, journalName=null, refType=null, unstructuredReference=
Hao X Y,
Luo S J,
Chen M Y,
He C H,
Wang T and
Wu H.
2024. Infrared small target detection with super-resolution and YOLO. Optics and Laser Technology,
177: #111221 [DOI:
10.1016/j.optlastec.2024.111221], articleTitle=Infrared small target detection with super-resolution and YOLO, refAbstract=null), Reference(id=1322963065926459915, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2021, volume=34, issue=null, pageStart=20230, pageEnd=20242, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=He J B, Erfani S M, Ma X J, Bailey J, Chi Y, Hua X S, journalName=Advances in Neural Information Processing Systems, refType=null, unstructuredReference=
He J B,
Erfani S M,
Ma X J,
Bailey J,
Chi Y and
Hua X S.
2021.
α-IoU: a family of power intersection over union losses for bounding box regression.
Advances in Neural Information Processing Systems,
34: 20230-20242, articleTitle=
α-IoU: a family of power intersection over union losses for bounding box regression, refAbstract=null), Reference(id=1322963066014540300, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=7, pageStart=null, pageEnd=677, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Hussain M, journalName=Machines, refType=null, unstructuredReference=
Hussain M.
2023. YOLO-v1 to YOLO-v8,the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection.
Machines,
11(7): #677 [DOI:
10.3390/machines11070677], articleTitle=YOLO-v1 to YOLO-v8,the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection, refAbstract=null), Reference(id=1322963066085843469, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=4, pageStart=1161, pageEnd=1175, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=Jia K X, Ma Z H, Zhu R, Li Y G, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Jia K X,
Ma Z H,
Zhu R and
Li Y G.
2022. Attention-mechanism-based light single shot multiBox detector modelling improvement for small object detection on the sea surface.
Journal of Image and Graphics,
27(4): 1161-1175, articleTitle=Attention-mechanism-based light single shot multiBox detector modelling improvement for small object detection on the sea surface, refAbstract=null), Reference(id=1322963066152952334, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=4, pageStart=1161, pageEnd=1175, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=贾可心, 马正华, 朱蓉, 李永刚, journalName=中国图象图形学报, refType=null, unstructuredReference=贾可心,马正华,朱蓉,李永刚.
2022. 注意力机制改进轻量SSD模型的海面小目标检测.
中国图象图形学报,
27(4): 1161-1175 [DOI:
10.11834/jig.200517], articleTitle=注意力机制改进轻量SSD模型的海面小目标检测, refAbstract=null), Reference(id=1322963066245227023, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=73, issue=null, pageStart=null, pageEnd=5015214, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Jiang L J, Yuan B X, Du J W, Chen B Y, Xie H F, Tian J, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=
Jiang L J,
Yuan B X,
Du J W,
Chen B Y,
Xie H F,
Tian J,
et al.
2024. MFFSODNet: multiscale feature fusion small object detection network for UAV aerial images.
IEEE Transactions on Instrumentation and Measurement,
73: #5015214 [DOI:
10.1109/TIM.2024.3381272], articleTitle=MFFSODNet: multiscale feature fusion small object detection network for UAV aerial images, refAbstract=null), Reference(id=1322963066333307408, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=3992, pageEnd=4003, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Kirillov A, Mintun E, Ravi N, Mao H Z, Rolland C, Gustafson L, journalName=null, refType=null, unstructuredReference=
Kirillov A,
Mintun E,
Ravi N,
Mao H Z,
Rolland C,
Gustafson L,
et al.
2023. Segment anything//Proceedings of 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Paris,France: IEEE: 3992-4003 [DOI:
10.1109/ICCV51070.2023.00371], articleTitle=Segment anything, refAbstract=null), Reference(id=1322963066438165009, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=9, pageStart=757, pageEnd=765, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Kulambayev B, Nurlybek M, Astaubayeva G, Tleuberdiyeva G, Zholdasbayev S, Tolep A, journalName=International Journal of Advanced Computer Science and Applications, refType=null, unstructuredReference=
Kulambayev B,
Nurlybek M,
Astaubayeva G,
Tleuberdiyeva G,
Zholdasbayev S and
Tolep A.
2023. Real-time road surface damage detection framework based on mask R-CNN model.
International Journal of Advanced Computer Science and Applications,
14(9): 757-765 [DOI:
10.14569/IJACSA.2023.0140979], articleTitle=Real-time road surface damage detection framework based on mask R-CNN model, refAbstract=null), Reference(id=1322963066526245394, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=14695, pageEnd=14706, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=Liang M F, Su J C, Schulter S, Garg S, Zhao S Y, Wu Y, journalName=null, refType=null, unstructuredReference=
Liang M F,
Su J C,
Schulter S,
Garg S,
Zhao S Y,
Wu Y,
et al.
2024. AIDE: an automatic data engine for object detection in autonomous driving//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,USA: IEEE: 14695-14706 [DOI:
10.1109/CVPR52733.2024.01392], articleTitle=AIDE: an automatic data engine for object detection in autonomous driving, refAbstract=null), Reference(id=1322963066622714387, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=740, pageEnd=755, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Lin T Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, journalName=null, refType=null, unstructuredReference=
Lin T Y,
Maire M,
Belongie S,
Hays J,
Perona P,
Ramanan D,
et al.
2014. Microsoft COCO: common objects in context//Proceedings of the 13th European Conference on Computer Vision (ECCV). Zurich,Switzerland: Springer: 740-755 [DOI:
10.1007/978-3-319-10602-1_48], articleTitle=Microsoft COCO: common objects in context, refAbstract=null), Reference(id=1322963066714989076, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=25, issue=10, pageStart=13863, pageEnd=13875, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Liu C G, Gao G S, Huang Z Y, Hu Z H, Liu Q J, Wang Y H, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=
Liu C G,
Gao G S,
Huang Z Y,
Hu Z H,
Liu Q J and
Wang Y H.
2024. YOLC: you only look clusters for tiny object detection in aerial images.
IEEE Transactions on Intelligent Transportation Systems,
25(10): 13863-13875 [DOI:
10.1109/TITS.2024.3386928], articleTitle=YOLC: you only look clusters for tiny object detection in aerial images, refAbstract=null), Reference(id=1322963066786292245, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=7507, pageEnd=7512, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=Liu S H, Zha J L, Sun J, Li Z, Wang G, journalName=null, refType=null, unstructuredReference=
Liu S H,
Zha J L,
Sun J,
Li Z and
Wang G.
2023. EdgeYOLO: an edge-real-time object detector//Proceedings of the 42nd Chinese Control Conference (CCC). Tianjin,China: IEEE: 7507-7512 [DOI:
10.23919/CCC58697.2023.10239786], articleTitle=EdgeYOLO: an edge-real-time object detector, refAbstract=null), Reference(id=1322963066865984022, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2021a, volume=172, issue=null, pageStart=null, pageEnd=114602, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Liu Y, Sun P, Wergeles N, Shang Y, journalName=Expert Systems with Applications, refType=null, unstructuredReference=
Liu Y,
Sun P,
Wergeles N and
Shang Y.
2021a. A survey and performance evaluation of deep learning methods for small object detection.
Expert Systems with Applications,
172: #114602 [DOI:
10.1016/j.eswa.2021.114602], articleTitle=A survey and performance evaluation of deep learning methods for small object detection, refAbstract=null), Reference(id=1322963066937287191, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2021b, volume=null, issue=null, pageStart=9992, pageEnd=10002, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Liu Z, Lin Y T, Cao Y, Hu H, Wei Y X, Zhang Z, journalName=null, refType=null, unstructuredReference=
Liu Z,
Lin Y T,
Cao Y,
Hu H,
Wei Y X,
Zhang Z,
et al.
2021b. Swin Transformer: hierarchical vision transformer using shifted windows//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal,Canada: IEEE: 9992-10002 [DOI:
10.1109/ICCV48922.2021.00986], articleTitle=Swin Transformer: hierarchical vision transformer using shifted windows, refAbstract=null), Reference(id=1322963067012784664, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=9, pageStart=2587, pageEnd=2615, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Pan X Y, Jia N X, Mu Y Z, Gao X R, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=
Pan X Y,
Jia N X,
Mu Y Z and
Gao X R.
2023. Survey of small object detection.
Journal of Image and Graphics,
28(9): 2587-2615, articleTitle=Survey of small object detection, refAbstract=null), Reference(id=1322963067092476441, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=9, pageStart=2587, pageEnd=2615, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=潘晓英, 贾凝心, 穆元震, 高炫蓉, journalName=中国图象图形学报, refType=null, unstructuredReference=潘晓英,贾凝心,穆元震,高炫蓉.
2023. 小目标检测研究综述.
中国图象图形学报,
28(9): 2587-2615 [DOI:
10.11834/jig.220455], articleTitle=小目标检测研究综述, refAbstract=null), Reference(id=1322963067188945434, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Rasheed M R, Coleman S, Gardiner B, Vance P, McAteer C, Nguyen K, journalName=null, refType=null, unstructuredReference=
Rasheed M R,
Coleman S,
Gardiner B,
Vance P,
McAteer C and
Nguyen K.
2024. An EfficientNet-based transfer learning system for defect classification in manufacturing//Proceedings of the 22nd IEEE International Conference on Industrial Informatics (INDIN). Beijing,China: IEEE: 1-7 [DOI:
10.1109/INDIN58382.2024.10774443], articleTitle=An EfficientNet-based transfer learning system for defect classification in manufacturing, refAbstract=null), Reference(id=1322963067277025819, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=779, pageEnd=788, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Redmon J, Divvala S, Girshick R, Farhadi A, journalName=null, refType=null, unstructuredReference=
Redmon J,
Divvala S,
Girshick R and
Farhadi A.
2016. You only look once: unified,real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas,USA: IEEE: 779-788 [DOI:
10.1109/CVPR.2016.91], articleTitle=You only look once: unified,real-time object detection, refAbstract=null), Reference(id=1322963067348328988, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=null, rfOrder=26, 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=1322963067423826461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=Sanders A, journalName=null, refType=null, unstructuredReference=
Sanders A.
2016. An Introduction to Unreal Engine 4. New York,USA: AK Peters/CRC Press., articleTitle=An Introduction to Unreal Engine 4. New York,USA: AK Peters/CRC Press, refAbstract=null), Reference(id=1322963067516101150, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2017, volume=19, issue=null, pageStart=221, pageEnd=248, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=Shen D G, Wu G R, Suk H I, journalName=Annual Review of Biomedical Engineering, refType=null, unstructuredReference=
Shen D G,
Wu G R and
Suk H I.
2017. Deep learning in medical image analysis.
Annual Review of Biomedical Engineering,
19: 221-248 [DOI:
10.1146/annurev-bioeng-071516-044442], articleTitle=Deep learning in medical image analysis, refAbstract=null), Reference(id=1322963069361594911, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=#3429, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=29, authorNames=Wang A, Chen H, Liu L H, Chen K, Lin Z J, Han J G, journalName=null, refType=null, unstructuredReference=
Wang A,
Chen H,
Liu L H,
Chen K,
Lin Z J,
Han J G,
et al.
2024. YOLOv10: real-time end-to-end object detection//Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver,Canada: Curran Associates Inc.: #3429, articleTitle=YOLOv10: real-time end-to-end object detection, refAbstract=null), Reference(id=1322963069437092384, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=7464, pageEnd=7475, url=null, language=null, rfNumber=null, rfOrder=30, authorNames=Wang C Y, Bochkovskiy A, Liao H Y M, journalName=null, refType=null, unstructuredReference=
Wang C Y,
Bochkovskiy A and
Liao H Y M.
2023. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,Canada: IEEE: 7464-7475 [DOI:
10.1109/CVPR52729.2023.00721], articleTitle=YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, refAbstract=null), Reference(id=1322963069508395553, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2110.13389.pdf, language=null, rfNumber=null, rfOrder=31, authorNames=Wang J W, Xu C, Yang W, Yu L, journalName=null, refType=null, unstructuredReference=
Wang J W,
Xu C,
Yang W and
Yu L.
2021. A normalized Gaussian Wasserstein distance for tiny object detection [EB/OL]. [2021-10-26]., articleTitle=A normalized Gaussian Wasserstein distance for tiny object detection, refAbstract=null), Reference(id=1322963069571310114, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2501.17983.pdf, language=null, rfNumber=null, rfOrder=32, authorNames=Wang X D, Peng Y X, Shen C M, journalName=null, refType=null, unstructuredReference=
Wang X D,
Peng Y X and
Shen C M.
2025. Efficient feature fusion for UAV object detection [EB/OL]. [2025-01-29]., articleTitle=Efficient feature fusion for UAV object detection, refAbstract=null), Reference(id=1322963069651001891, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2026, volume=170, issue=null, pageStart=null, pageEnd=105770, url=null, language=null, rfNumber=null, rfOrder=33, authorNames=Wu K P, Xu Y F, Zhang J P, journalName=Digital Signal Processing, refType=null, unstructuredReference=
Wu K P,
Xu Y F and
Zhang J P.
2026. Lightweight multi-scale dynamic feature focusing network integrating spatial channel attention mechanism for autonomous driving object detection.
Digital Signal Processing,
170: #105770 [DOI:
10.1016/j.dsp.2025.105770], articleTitle=Lightweight multi-scale dynamic feature focusing network integrating spatial channel attention mechanism for autonomous driving object detection, refAbstract=null), Reference(id=1322963069726499364, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=9202, pageEnd=9210, url=null, language=null, rfNumber=null, rfOrder=34, authorNames=Yang J N, Liu S L, Wu J J, Su X Y, Hai N, Huang X L, journalName=Pinwheel-shaped convolution and scale-based dynamic loss for infrared small target detection. Proceedings of the 39th AAAI Conference on Artificial Intelligence, refType=null, unstructuredReference=
Yang J N,
Liu S L,
Wu J J,
Su X Y,
Hai N and
Huang X L.
2025.
Pinwheel-shaped convolution and scale-based dynamic loss for infrared small target detection. Proceedings of the 39th AAAI Conference on Artificial Intelligence. Philadelphia,USA: AAAI Press: 9202-9210 [DOI:
10.1609/aaai.v39i9.32996], articleTitle=null, refAbstract=null), Reference(id=1322963069810385445, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=6, pageStart=2872, pageEnd=2893, url=null, language=null, rfNumber=null, rfOrder=35, authorNames=Ye M, Shen J B, Lin G J, Xiang T, Shao L, Hoi S C H, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=
Ye M,
Shen J B,
Lin G J,
Xiang T,
Shao L and
Hoi S C H.
2022. Deep learning for person re-identification: a survey and outlook.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
44(6): 2872-2893 [DOI:
10.1109/TPAMI.2021.3054775], articleTitle=Deep learning for person re-identification: a survey and outlook, refAbstract=null), Reference(id=1322963069898465830, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2025, volume=47, issue=7, pageStart=6088, pageEnd=6096, url=null, language=null, rfNumber=null, rfOrder=36, authorNames=Ying X Y, Xiao C, An W, Li R J, He X, Li B Y, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=
Ying X Y,
Xiao C,
An W,
Li R J,
He X,
Li B Y,
et al.
2025. Visible-thermal tiny object detection: a benchmark dataset and baselines.
IEEE Transactions on Pattern Analysis and Machine Intelligence,
47(7): 6088-6096 [DOI:
10.1109/TPAMI.2025.3544621], articleTitle=Visible-thermal tiny object detection: a benchmark dataset and baselines, refAbstract=null), Reference(id=1322963069978157607, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=516, pageEnd=520, url=null, language=null, rfNumber=null, rfOrder=37, authorNames=Yu J H, Jiang Y N, Wang Z Y, Cao Z M, Huang T, journalName=null, refType=null, unstructuredReference=
Yu J H,
Jiang Y N,
Wang Z Y,
Cao Z M and
Huang T.
2016. UnitBox: an advanced object detection network//Proceedings of the 24th ACM International Conference on Multimedia. Amsterdam,the Netherlands: ACM: 516-520 [DOI:
10.1145/2964284.2967274], articleTitle=UnitBox: an advanced object detection network, refAbstract=null), Reference(id=1322963070070432296, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=3, pageStart=1787, pageEnd=1803, url=null, language=null, rfNumber=null, rfOrder=38, authorNames=Zeng S, Yang W Z, Jiao Y Y, Geng L, Chen X T, journalName=The Visual Computer, refType=null, unstructuredReference=
Zeng S,
Yang W Z,
Jiao Y Y,
Geng L and
Chen X T.
2024. SCA-YOLO: a new small object detection model for UAV images.
The Visual Computer,
40(3): 1787-1803 [DOI:
10.1007/s00371-023-02886-y], articleTitle=SCA-YOLO: a new small object detection model for UAV images, refAbstract=null), Reference(id=1322963070141735465, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=47, pageEnd=54, url=null, language=null, rfNumber=null, rfOrder=39, authorNames=Zhang G, Zhao X, journalName=null, refType=null, unstructuredReference=
Zhang G and
Zhao X.
2025. An improved RT-DETR model for small object detection on construction sites//Proceedings of the 11th International Conference on Computing and Artificial Intelligence (ICCAI). Kyoto,Japan: IEEE: 47-54 [DOI:
10.1109/ICCAI66501.2025.00015], articleTitle=An improved RT-DETR model for small object detection on construction sites, refAbstract=null), Reference(id=1322963070221427242, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=14, pageStart=3986, pageEnd=3999, url=null, language=null, rfNumber=null, rfOrder=40, authorNames=Zhang Y F, Yu J Y, Wang Y Y, Tang S, Li H, Xin Z Y, journalName=IET Image Processing, refType=null, unstructuredReference=
Zhang Y F,
Yu J Y,
Wang Y Y,
Tang S,
Li H,
Xin Z Y,
et al.
2023. Small object detection based on hierarchical attention mechanism and multi-scale separable detection.
IET Image Processing,
17(14): 3986-3999 [DOI:
10.1049/ipr2.12912], articleTitle=Small object detection based on hierarchical attention mechanism and multi-scale separable detection, refAbstract=null), Reference(id=1322963070296924715, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=16965, pageEnd=16974, url=null, language=null, rfNumber=null, rfOrder=41, authorNames=Zhao Y A, Lyu W Y, Xu S L, Wei J M, Wang G Z, Dang Q Q, journalName=null, refType=null, unstructuredReference=
Zhao Y A,
Lyu W Y,
Xu S L,
Wei J M,
Wang G Z,
Dang Q Q,
et al.
2024. DETRs beat YOLOs on real-time object detection//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle,USA: IEEE: 16965-16974 [DOI:
10.1109/CVPR52733.2024.01605], articleTitle=DETRs beat YOLOs on real-time object detection, refAbstract=null), Reference(id=1322963070355644972, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2025, volume=261, issue=null, pageStart=null, pageEnd=104489, url=null, language=null, rfNumber=null, rfOrder=42, authorNames=Zheng Y C, Jing Y X, Zhao J F, Cui G M, journalName=Computer Vision and Image Understanding, refType=null, unstructuredReference=
Zheng Y C,
Jing Y X,
Zhao J F and
Cui G M.
2025. LAM-YOLO: drones-based small object detection on lighting-occlusion attention mechanism YOLO.
Computer Vision and Image Understanding,
261: #104489 [DOI:
10.1016/j.cviu.2025.104489], articleTitle=LAM-YOLO: drones-based small object detection on lighting-occlusion attention mechanism YOLO, refAbstract=null), Reference(id=1322963070422753837, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=12993, pageEnd=13000, url=null, language=null, rfNumber=null, rfOrder=43, authorNames=Zheng Z H, Wang P, Liu W, Li J Z, Ye R G, Ren D W, journalName=null, refType=null, unstructuredReference=
Zheng Z H,
Wang P,
Liu W,
Li J Z,
Ye R G and
Ren D W.
2020. Distance-IoU loss: faster and better learning for bounding box regression//Proceedings of the 34th AAAI Conference on Artificial Intelligence. New York,USA: AAAI Press: 12993-13000 [DOI:
10.1609/aaai.v34i07.6999], articleTitle=Distance-IoU loss: faster and better learning for bounding box regression, refAbstract=null), Reference(id=1322963070485668398, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=#132132, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=44, authorNames=Zhou Y, Jiang Y T, Yang Z L, Li X X, Yang Y, Wang Y, journalName=null, refType=null, unstructuredReference=
Zhou Y,
Jiang Y T,
Yang Z L,
Li X X,
Yang Y,
Wang Y,
et al.
2024. A small object detection method based on the attention mechanism and multi-level feature fusion//Proceedings of 2024 International Conference on Image Processing and Artificial Intelligence. [s.l.]:SPIE: #132132R [DOI:
10.1117/12.3035229], articleTitle=A small object detection method based on the attention mechanism and multi-level feature fusion, refAbstract=null), Reference(id=1322963070548582959, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=10323, pageEnd=10333, url=null, language=null, rfNumber=null, rfOrder=45, authorNames=Zhu L, Wang X J, Ke Z H, Zhang W, Lau R, journalName=null, refType=null, unstructuredReference=
Zhu L,
Wang X J,
Ke Z H,
Zhang W and
Lau R.
2023. BiFormer: vision transformer with bi-level routing attention//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver,Canada: IEEE: 10323-10333 [DOI:
10.1109/CVPR52729.2023.00995], articleTitle=BiFormer: vision transformer with bi-level routing attention, refAbstract=null), Reference(id=1322963070615691824, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, doi=null, pmid=null, pmcid=null, year=2023, volume=111, issue=3, pageStart=257, pageEnd=276, url=null, language=null, rfNumber=null, rfOrder=46, authorNames=Zou Z X, Chen K Y, Shi Z W, Guo Y H, Ye J P, journalName=Proceedings of the IEEE, refType=null, unstructuredReference=
Zou Z X,
Chen K Y,
Shi Z W,
Guo Y H and
Ye J P.
2023. Object detection in 20 years: a survey.
Proceedings of the IEEE,
111(3): 257-276 [DOI:
10.1109/JPROC.2023.3238524], articleTitle=Object detection in 20 years: a survey, refAbstract=null)], funds=[Fund(id=1322963063246299648, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, awardId=null, language=EN, fundingSource=National Natural Science Foundation of China (42361071,42261061);Guangxi Key R&D Program,China (ZG2504240008);Guangxi Postgraduate Education Innovation Program (YCBZ2024165), fundOrder=null, country=null), Fund(id=1322963064865300993, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, awardId=null, language=CN, fundingSource=国家自然科学基金项目(42361071,42261061);广西重点研发计划资助(ZG2504240008);广西研究生教育创新计划项目(YCBZ2024165), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322963054064968103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=1, ext=[AuthorCompanyExt(id=1322963054077551016, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China), AuthorCompanyExt(id=1322963054094328233, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054064968103, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1 桂林电子科技大学电子工程与自动化学院,桂林 541004)]), AuthorCompany(id=1322963054165631402, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=2, ext=[AuthorCompanyExt(id=1322963054174020011, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054165631402, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2 Guangxi Academy of Sciences,Nanning 530000,China), AuthorCompanyExt(id=1322963054186602924, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054165631402, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2 广西科学院,南宁 530000)]), AuthorCompany(id=1322963054266294701, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, xref=3, ext=[AuthorCompanyExt(id=1322963054270489006, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054266294701, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3 Key Laboratory of Intelligent Integrated Automation, Guangxi Higher Education Institutions,Guilin 541004,China), AuthorCompanyExt(id=1322963054278877615, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, companyId=1322963054266294701, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3 智能综合自动化广西高校重点实验室,桂林 541004)])], figs=[ArticleFig(id=1322963058301215194, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.1, caption=
Diagram of SOD-YOLO network, figureFileSmall=NS+iDjPEb5YRLljGiVPEGg==, figureFileBig=QWETjRFfeZoY/eD7DuugOA==, tableContent=null), ArticleFig(id=1322963058372518363, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图1, caption=
SOD-YOLO网络示意, figureFileSmall=NS+iDjPEb5YRLljGiVPEGg==, figureFileBig=QWETjRFfeZoY/eD7DuugOA==, tableContent=null), ArticleFig(id=1322963058569650652, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.2, caption=
Diagram of four-channel input under video background differential preprocessing, figureFileSmall=JDjYu1w+eGajIXS2yWRVFw==, figureFileBig=sPXuwGGhyWpRFxuY4YMOWw==, tableContent=null), ArticleFig(id=1322963058624176605, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图2, caption=
视频背景差分四通道输入示意, figureFileSmall=JDjYu1w+eGajIXS2yWRVFw==, figureFileBig=sPXuwGGhyWpRFxuY4YMOWw==, tableContent=null), ArticleFig(id=1322963058708062686, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.3, caption=
Diagram of MSFP structure, figureFileSmall=v+BXlNVKDAuyVRDJ7jwSBA==, figureFileBig=a1hf4sBJcP12+foFsScgIg==, tableContent=null), ArticleFig(id=1322963060406755807, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图3, caption=
MSFP网络结构, figureFileSmall=v+BXlNVKDAuyVRDJ7jwSBA==, figureFileBig=a1hf4sBJcP12+foFsScgIg==, tableContent=null), ArticleFig(id=1322963060490641888, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.4, caption=
Diagram of SOD-YOLO decoupled head ((a) coupled head structure; (b) decoupled head structure), figureFileSmall=mZDw3W1djhmo7u2lBFIwRg==, figureFileBig=j4r6Si3SdGumeK0a93z5NA==, tableContent=null), ArticleFig(id=1322963060603888097, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图4, caption=
SOD-YOLO解耦合头结构, figureFileSmall=mZDw3W1djhmo7u2lBFIwRg==, figureFileBig=j4r6Si3SdGumeK0a93z5NA==, tableContent=null), ArticleFig(id=1322963060691968482, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.5, caption=
Generation pipeline of small object samples in static images through copy-and-paste technique guided by semantic segmentation model SAM2, figureFileSmall=/1xQuXF7EGyrlof8QVgiXQ==, figureFileBig=y71SZHbRuKs4NVXkDQa/+Q==, tableContent=null), ArticleFig(id=1322963060780048867, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图5, caption=
SAM2掩膜下的静态影像小目标样本复制粘贴生成流程, figureFileSmall=/1xQuXF7EGyrlof8QVgiXQ==, figureFileBig=y71SZHbRuKs4NVXkDQa/+Q==, tableContent=null), ArticleFig(id=1322963060863934948, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.6, caption=
Diagram of generating small target samples for dynamic videos using UE virtual character assets, figureFileSmall=X4wFOO1psVFHPOAKSyaG2g==, figureFileBig=VWMaZPrDeUl6THDCRgsJ/Q==, tableContent=null), ArticleFig(id=1322963060952015333, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图6, caption=
基于UE虚拟人物资产的视频小目标样本合成示意, figureFileSmall=X4wFOO1psVFHPOAKSyaG2g==, figureFileBig=VWMaZPrDeUl6THDCRgsJ/Q==, tableContent=null), ArticleFig(id=1322963061040095718, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.7, caption=
The inference results of different network models, figureFileSmall=hrYLfV8y1yRMYnwcTzSX/g==, figureFileBig=NFAWhzMJ1nrjE8hgVL8Hcg==, tableContent=null), ArticleFig(id=1322963061128176103, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图7, caption=
不同网络模型推理结果示意, figureFileSmall=hrYLfV8y1yRMYnwcTzSX/g==, figureFileBig=NFAWhzMJ1nrjE8hgVL8Hcg==, tableContent=null), ArticleFig(id=1322963061233033704, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.8, caption=
Visualization results of small object detection on the VT-TOD dataset, figureFileSmall=dWLK/kgRqnnO8Uanfua4rA==, figureFileBig=BU6JAt2qD69iSdiGWm45rQ==, tableContent=null), ArticleFig(id=1322963061325308393, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图8, caption=
VT-TOD数据集上的小目标检测可视化结果, figureFileSmall=dWLK/kgRqnnO8Uanfua4rA==, figureFileBig=BU6JAt2qD69iSdiGWm45rQ==, tableContent=null), ArticleFig(id=1322963061434360298, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.9, caption=
Heat map of object detection in college campus scene under different module combinations ((a) original image; (b) YOLOv7 heat map; (c) heat map of video pre-differential and routing attention mechanism; (d) heat map of multi-scale feature fusion module; (e) heat map of multi-scale feature fusion,α-CIoU loss,and decoupled head; (f) heat map of all the modules), figureFileSmall=DsqQ3a9syYHawmpucDj/1A==, figureFileBig=1GCozMnAbGw1w2l6dt04sg==, tableContent=null), ArticleFig(id=1322963061530829291, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图9, caption=
不同模块组合下大学校园场景行人目标检测热力图, figureFileSmall=DsqQ3a9syYHawmpucDj/1A==, figureFileBig=1GCozMnAbGw1w2l6dt04sg==, tableContent=null), ArticleFig(id=1322963061610521068, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.10, caption=
Visualization of network inference results before and after adding UE synthetic data in the college campus scenario, figureFileSmall=0D5YceNIUMQQDy05vtnbRA==, figureFileBig=xxhYqLKT8nWyxJPOjN/k6Q==, tableContent=null), ArticleFig(id=1322963061681824237, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图10, caption=
大学校园场景添加UE合成数据前后的网络推理结果对比可视化示意图((a) ground truth; (b) inference without synthetic data;
(c) inference with synthetic data)
, figureFileSmall=0D5YceNIUMQQDy05vtnbRA==, figureFileBig=xxhYqLKT8nWyxJPOjN/k6Q==, tableContent=null), ArticleFig(id=1322963061757321710, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.11, caption=
Visualization of network inference results before and after adding UE synthetic data in the highway service area scenario ((a) ground truth; (b) inference without synthetic data; (c) inference with synthetic data), figureFileSmall=W/V6zK6PyqmPNf6wwFfbOw==, figureFileBig=nAr3c4nSLWrTwTiYl9l1BQ==, tableContent=null), ArticleFig(id=1322963061862179311, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图11, caption=
高速公路服务区场景添加UE合成数据前后的网络推理结果对比可视化示意图, figureFileSmall=W/V6zK6PyqmPNf6wwFfbOw==, figureFileBig=nAr3c4nSLWrTwTiYl9l1BQ==, tableContent=null), ArticleFig(id=1322963061925093872, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Fig.12, caption=
Visualization of network inference results before and after adding UE synthetic data in the construction site scenario, figureFileSmall=To08KP+iahopMKP3moNICA==, figureFileBig=gmK2q58gQbRdYdALVs1fog==, tableContent=null), ArticleFig(id=1322963061983814129, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=图12, caption=
建筑工地场景添加UE合成数据前后的网络推理结果对比可视化示意图((a) ground truth; (b) inference without synthetic data;
(c) inference with synthetic data)
, figureFileSmall=To08KP+iahopMKP3moNICA==, figureFileBig=gmK2q58gQbRdYdALVs1fog==, tableContent=null), ArticleFig(id=1322963062046728690, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 1, caption=
Comparative experimental results of construction site scenes/%, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数/M | AP | AP50 | AP75 | AP50s |
|---|
| YOLOv7 | 28.1 | 22.8 | 52.6 | 12.1 | 46.3 |
| YOLOv8 | 28.6 | 21.3 | 51.1 | 12.1 | 48.8 |
| YOLOv10 | 21.6 | 20.3 | 50.5 | 12.7 | 44.1 |
| RT-DETR | 45.9 | 25.3 | 57.5 | 12.0 | 44.6 |
| Faster R-CNN | - | 21.5 | 54.3 | 13.1 | 48.5 |
| YOLC | 43.3 | 22.9 | 55.2 | 12.6 | 45.6 |
| Drone-YOLO | 40.5 | 25.4 | 56.9 | 11.9 | 52.7 |
| SOD-YOLO (本文) | 36.4 | 24.5 | 56.2 | 13.5 | 53.9 |
), ArticleFig(id=1322963062118031859, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表1, caption=
建筑工地场景对比实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数/M | AP | AP50 | AP75 | AP50s |
|---|
| YOLOv7 | 28.1 | 22.8 | 52.6 | 12.1 | 46.3 |
| YOLOv8 | 28.6 | 21.3 | 51.1 | 12.1 | 48.8 |
| YOLOv10 | 21.6 | 20.3 | 50.5 | 12.7 | 44.1 |
| RT-DETR | 45.9 | 25.3 | 57.5 | 12.0 | 44.6 |
| Faster R-CNN | - | 21.5 | 54.3 | 13.1 | 48.5 |
| YOLC | 43.3 | 22.9 | 55.2 | 12.6 | 45.6 |
| Drone-YOLO | 40.5 | 25.4 | 56.9 | 11.9 | 52.7 |
| SOD-YOLO (本文) | 36.4 | 24.5 | 56.2 | 13.5 | 53.9 |
), ArticleFig(id=1322963062185140724, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 2, caption=
Comparative experimental results of highway, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数/M | AP | AP50 | AP75 | AP50s |
|---|
| YOLOv7 | 73.1 | 38.5 | 80.2 | 28.4 | 40.3 |
| YOLOv8 | 75.6 | 38.9 | 81.3 | 28.0 | 42.1 |
| YOLOv10 | 70.5 | 37.7 | 79.6 | 27.5 | 41.6 |
| RT-DETR | 102.1 | 40.1 | 82.5 | 28.8 | 42.1 |
| Faster R-CNN | - | 39.5 | 80.4 | 27.6 | 41.8 |
| YOLC | 89.3 | 42.4 | 83.3 | 28.1 | 43.6 |
| Drone-YOLO | 80.9 | 41.6 | 82.5 | 27.5 | 42.5 |
| SOD-YOLO (本文) | 92.7 | 42.6 | 82.4 | 29.5 | 44.3 |
), ArticleFig(id=1322963062289998325, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表2, caption=
高速公路服务区场景对比实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数/M | AP | AP50 | AP75 | AP50s |
|---|
| YOLOv7 | 73.1 | 38.5 | 80.2 | 28.4 | 40.3 |
| YOLOv8 | 75.6 | 38.9 | 81.3 | 28.0 | 42.1 |
| YOLOv10 | 70.5 | 37.7 | 79.6 | 27.5 | 41.6 |
| RT-DETR | 102.1 | 40.1 | 82.5 | 28.8 | 42.1 |
| Faster R-CNN | - | 39.5 | 80.4 | 27.6 | 41.8 |
| YOLC | 89.3 | 42.4 | 83.3 | 28.1 | 43.6 |
| Drone-YOLO | 80.9 | 41.6 | 82.5 | 27.5 | 42.5 |
| SOD-YOLO (本文) | 92.7 | 42.6 | 82.4 | 29.5 | 44.3 |
), ArticleFig(id=1322963062352912886, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 3, caption=
Comparative experimental results of college campus scenes /%, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数/M | AP | AP50 | AP75 | AP50s |
|---|
| YOLOv7 | 86.3 | 33.7 | 70.6 | 22.9 | 36.1 |
| YOLOv8 | 78.5 | 32.4 | 72.5 | 22.5 | 35.2 |
| YOLOv10 | 74.2 | 32.0 | 69.3 | 24.4 | 33.5 |
| RT-DETR | 104.6 | 37.2 | 72.8 | 22.7 | 39.9 |
| Faster R-CNN | - | 35.2 | 72.7 | 24.1 | 32.6 |
| YOLC | 91.8 | 38.3 | 71.5 | 25.2 | 40.4 |
| Drone-YOLO | 84.1 | 36.6 | 71.4 | 24.5 | 41.1 |
| SOD-YOLO (本文) | 95.4 | 38.6 | 71.5 | 25.4 | 41.1 |
), ArticleFig(id=1322963062420021751, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表3, caption=
大学校园场景对比实验结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数/M | AP | AP50 | AP75 | AP50s |
|---|
| YOLOv7 | 86.3 | 33.7 | 70.6 | 22.9 | 36.1 |
| YOLOv8 | 78.5 | 32.4 | 72.5 | 22.5 | 35.2 |
| YOLOv10 | 74.2 | 32.0 | 69.3 | 24.4 | 33.5 |
| RT-DETR | 104.6 | 37.2 | 72.8 | 22.7 | 39.9 |
| Faster R-CNN | - | 35.2 | 72.7 | 24.1 | 32.6 |
| YOLC | 91.8 | 38.3 | 71.5 | 25.2 | 40.4 |
| Drone-YOLO | 84.1 | 36.6 | 71.4 | 24.5 | 41.1 |
| SOD-YOLO (本文) | 95.4 | 38.6 | 71.5 | 25.4 | 41.1 |
), ArticleFig(id=1322963062512296440, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 4, caption=
Performance comparison of small object detection on the VT-TOD public dataset, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数量/M | 精确率 | AP50:95 | APs | APm |
|---|
| QueryDet | 38.6 | 43.6 | 33.8 | 45.2 | 39.8 |
| YOLOC | 68.9 | 56.8 | 42.4 | 59.2 | 54.6 |
| Drone-YOLO | 78.8 | 58.9 | 48.1 | 60.8 | 52.0 |
| SOD-YOLO | 74.4 | 61.4 | 52.3 | 63.5 | 58.2 |
), ArticleFig(id=1322963062587793913, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表4, caption=
VT-TOD公共数据集上的小目标检测性能对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 参数量/M | 精确率 | AP50:95 | APs | APm |
|---|
| QueryDet | 38.6 | 43.6 | 33.8 | 45.2 | 39.8 |
| YOLOC | 68.9 | 56.8 | 42.4 | 59.2 | 54.6 |
| Drone-YOLO | 78.8 | 58.9 | 48.1 | 60.8 | 52.0 |
| SOD-YOLO | 74.4 | 61.4 | 52.3 | 63.5 | 58.2 |
), ArticleFig(id=1322963062667485690, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 5, caption=
Ablation experiment, figureFileSmall=null, figureFileBig=null, tableContent=
| 视频背景差分 | 双层路由注意力机制 | 多尺度特征融合 | α-CIoU损失函数 | 多任务解耦 | AP | AP50 | AP75 | APs |
|---|
| - | - | - | - | - | 33.7 | 69.6 | 21.9 | 36.1 |
| √ | - | - | - | - | 37.4 | 70.3 | 24.4 | 40.8 |
| - | √ | - | - | - | 36.8 | 71.3 | 22.6 | 40.2 |
| - | - | √ | - | - | 35.1 | 71.1 | 23.2 | 38.9 |
| - | - | - | √ | - | 34.5 | 70.8 | 24.7 | 37.8 |
| - | - | - | - | √ | 32.9 | 70.4 | 22.7 | 36.4 |
| √ | √ | - | - | - | 37.9 | 70.5 | 24.6 | 40.6 |
| - | - | √ | √ | √ | 36.6 | 71.0 | 23.8 | 40.0 |
| √ | √ | √ | √ | √ | 38.6 | 71.3 | 25.4 | 41.1 |
), ArticleFig(id=1322963062747177467, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表5, caption=
消融实验
, figureFileSmall=null, figureFileBig=null, tableContent=
| 视频背景差分 | 双层路由注意力机制 | 多尺度特征融合 | α-CIoU损失函数 | 多任务解耦 | AP | AP50 | AP75 | APs |
|---|
| - | - | - | - | - | 33.7 | 69.6 | 21.9 | 36.1 |
| √ | - | - | - | - | 37.4 | 70.3 | 24.4 | 40.8 |
| - | √ | - | - | - | 36.8 | 71.3 | 22.6 | 40.2 |
| - | - | √ | - | - | 35.1 | 71.1 | 23.2 | 38.9 |
| - | - | - | √ | - | 34.5 | 70.8 | 24.7 | 37.8 |
| - | - | - | - | √ | 32.9 | 70.4 | 22.7 | 36.4 |
| √ | √ | - | - | - | 37.9 | 70.5 | 24.6 | 40.6 |
| - | - | √ | √ | √ | 36.6 | 71.0 | 23.8 | 40.0 |
| √ | √ | √ | √ | √ | 38.6 | 71.3 | 25.4 | 41.1 |
), ArticleFig(id=1322963062864617980, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 6, caption=
Experimental results on model performance with addition of UE synthetic data, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 真实数据 | UE数据 | AP/% | AP50/% |
|---|
| YOLOv7 | 6 000 | - | 32.7 | 76.6 |
| 1 500 | 39.3 | 80.8 |
| 3 000 | 37.1 | 78.7 |
| YOLOv8 | 6 000 | - | 33.5 | 77.9 |
| 1 500 | 38.2 | 81.5 |
| 3 000 | 39.2 | 80.4 |
| RT-DETR | 6 000 | - | 36.2 | 78.6 |
| 1 500 | 39.4 | 81.9 |
| 3 000 | 40.3 | 81.5 |
| SOD-YOLO | 6 000 | - | 37.5 | 79.8 |
| 1 500 | 41.0 | 82.7 |
| 3 000 | 42.1 | 82.3 |
), ArticleFig(id=1322963062986252797, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表6, caption=
添加UE合成数据模型的性能变化实验
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 真实数据 | UE数据 | AP/% | AP50/% |
|---|
| YOLOv7 | 6 000 | - | 32.7 | 76.6 |
| 1 500 | 39.3 | 80.8 |
| 3 000 | 37.1 | 78.7 |
| YOLOv8 | 6 000 | - | 33.5 | 77.9 |
| 1 500 | 38.2 | 81.5 |
| 3 000 | 39.2 | 80.4 |
| RT-DETR | 6 000 | - | 36.2 | 78.6 |
| 1 500 | 39.4 | 81.9 |
| 3 000 | 40.3 | 81.5 |
| SOD-YOLO | 6 000 | - | 37.5 | 79.8 |
| 1 500 | 41.0 | 82.7 |
| 3 000 | 42.1 | 82.3 |
), ArticleFig(id=1322963063070138878, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=EN, label=Table 7, caption=
Experimental results on model performance under a constant training data volume with gradually reduced real data proportion, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 真实数据 | UE数据 | AP/% | AP50/% |
|---|
| YOLOv7 | 6 000 | 2 000 | 36.8 | 72.3 |
| 4 000 | 4 000 | 34.4 | 66.9 |
| - | 8 000 | 18.5 | 38.8 |
| YOLOv8 | 6 000 | 2 000 | 39.2 | 75.5 |
| 4 000 | 4 000 | 32.5 | 69.6 |
| - | 8 000 | 20.8 | 42.8 |
| RT-DETR | 6 000 | 2 000 | 39.5 | 78.2 |
| 4 000 | 4 000 | 40.8 | 70.3 |
| - | 8 000 | 28.3 | 50.6 |
| SOD-YOLO | 6 000 | 2 000 | 39.9 | 78.7 |
| 4 000 | 4 000 | 41.0 | 70.8 |
| - | 8 000 | 29.0 | 51.2 |
), ArticleFig(id=1322963063149830655, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963049459622284, language=CN, label=表7, caption=
保持训练数据总量不变减少真实数据比例实验
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 真实数据 | UE数据 | AP/% | AP50/% |
|---|
| YOLOv7 | 6 000 | 2 000 | 36.8 | 72.3 |
| 4 000 | 4 000 | 34.4 | 66.9 |
| - | 8 000 | 18.5 | 38.8 |
| YOLOv8 | 6 000 | 2 000 | 39.2 | 75.5 |
| 4 000 | 4 000 | 32.5 | 69.6 |
| - | 8 000 | 20.8 | 42.8 |
| RT-DETR | 6 000 | 2 000 | 39.5 | 78.2 |
| 4 000 | 4 000 | 40.8 | 70.3 |
| - | 8 000 | 28.3 | 50.6 |
| SOD-YOLO | 6 000 | 2 000 | 39.9 | 78.7 |
| 4 000 | 4 000 | 41.0 | 70.8 |
| - | 8 000 | 29.0 | 51.2 |
)], 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.250491, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.250491, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.250491, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.250491, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1792080000000, fullTextJson=null, articleText=null, reference=null)