Article(id=1322963022628651188, tenantId=1146029695717560320, journalId=1249024232475115590, issueId=1322962941087195876, articleNumber=null, orderNo=null, doi=10.11834/jig.250563, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1763049600000, receivedDateStr=2025-11-14, revisedDate=1769702400000, revisedDateStr=2026-01-30, acceptedDate=null, acceptedDateStr=null, onlineDate=1793348564058, onlineDateStr=2026-10-30, pubDate=1792080000000, pubDateStr=2026-10-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793348564058, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793348564058, creator=13701087609, updateTime=1793348564058, 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=3572, endPage=3589, ext={EN=ArticleExt(id=1322963022859337909, articleId=1322963022628651188, tenantId=1146029695717560320, journalId=1249024232475115590, language=EN, title=Construction and validation of a high-resolution multitemporal remote sensing change detection dataset, columnId=1322961445507440644, journalTitle=Journal of Image and Graphics, columnName=Dataset, runingTitle=null, highlight=null, articleAbstract=
Objective

The acquisition of land surface change information is a fundamental pathway for understanding the evolution of the natural environment and the impacts of human activities. Land surface changes reflect the joint influence of natural processes and anthropogenic drivers on landscape pattern evolution. Such changes are not only governed by natural factors but are also closely intertwined with social and economic development. Timely and accurate monitoring and identification of these changes are crucial for gaining deeper insights into regional ecological succession and urban expansion processes,and they provide essential scientific support for territorial spatial planning,ecological and environmental protection,and social governance. Remote sensing change detection is an important research direction in the fields of remote sensing and geographic information science,and it has attracted increasing attention in recent years. The core objective of remote sensing change detection is to identify considerable changes in land-cover elements within the same geographical area across different time points by analyzing bitemporal or multitemporal remote sensing imagery. Most existing studies focus on bitemporal change detection. Although substantial progress has been achieved in terms of detection accuracy and computational efficiency,bitemporal approaches remain inherently limited in their ability to model temporal dynamics. In real-world scenarios,land surface changes often exhibit continuity,stage-wise progression,and multiscale temporal characteristics. Typical examples include the gradual expansion of urban areas,seasonal degradation and recovery of vegetation,and nonlinear postdisaster land surface restoration processes. Relying solely on two temporal snapshots makes it difficult to characterize such long-term evolutionary trends and complex dynamic patterns,and it also limits the ability to uncover latent trends associated with gradual or periodic changes. Moreover,given that only two temporal images are involved,bitemporal approaches are more susceptible to pseudo changes and misclassification when confronted with illumination variations,observation noise,and other acquisition-related inconsistencies. Consequently,exploring multitemporal change detection to better capture the dynamic evolution of land surfaces has become an important research direction. However,from a data perspective,high-resolution,high-quality multitemporal remote sensing change detection datasets that cover diverse land surface change types remain scarce. Most widely used change detection datasets remain limited to bitemporal imagery with corresponding annotations,primarily describing changes between two discrete time points. These datasets are often constrained in terms of the number of temporal phases,spatial coverage,image scale,and temporal span. As a result,they are insufficient for modeling and analyzing long-term,stage-wise land surface evolution processes,particularly in complex application scenarios such as urban expansion and ecological transformation.To address these limitations,this study constructs a high-resolution,multiregional,and multitemporal remote sensing change detection dataset,termed HR-MTCD (high-resolution multitemporal change detection),with the aim of providing fundamental data support for dynamic land surface evolution modeling.

Method

The dataset covers five representative regions in China,including the Yangtze River Delta,the Pearl River Delta,the Beijing-Tianjin-Hebei region,the Chengdu-Chongqing region,and Northwest China. It integrates multiple types of land surface changes related to urban development and ecological evolution. The dataset spans a five-year period,with changes annotated at one-year intervals,and consists of 1 601 change groups and 8 005 remote sensing images with a spatial resolution of approximately 0.5 meters. The change categories primarily focus on prominent land surface changes,such as building construction and demolition,and large-scale vegetation changes while covering typical scenarios related to urban growth and ecological dynamics. This design ensures the dataset’s practical applicability and relevance,providing robust support for research on diverse land surface changes and for the development of multitemporal change detection algorithms.

Result

Systematic experiments conducted using several mainstream change detection models reveal performance differences among models and validate the usability and the inherent challenges of the proposed high-resolution multitemporal dataset in real-world change detection tasks. Within a unified experimental framework,we further design progressive cross-temporal extension experiments. By comparing detection performance as training data from different temporal spans are incrementally incorporated,we evaluate the influence of multitemporal data on a model’s ability to recognize long-term,nonlinear,or gradual land surface changes. Experimental results demonstrate that the temporal dimension information contained in multitemporal remote sensing imagery plays a fundamental role in change detection tasks,offering new perspectives for models to understand dynamic land-cover evolution.

Conclusion

Overall,the construction of the HR-MTCD dataset provides an important data foundation for advancing remote sensing change detection from discrete bitemporal change identification toward comprehensive modeling of multitemporal land surface evolution processes.In future work,the dataset will be continuously expanded to cover a broader range of geographical regions and longer temporal spans to better capture diverse land surface dynamics under different environmental and socioeconomic conditions. In addition,we plan to incorporate multisource remote sensing modalities progressively,including optical imagery,synthetic aperture radar,and LiDAR data,thereby enabling complementary representations of land surface structure,texture,and physical properties. Beyond geometric and radiometric changes,semantic-level change information will also be introduced to describe higher-level land-cover transitions and functional transformations. The dataset is publicly available at https://doi.org/10.57760/sciencedb.j00240.00110.

, authors=Jianquan Zhou1, 2, Jingbo Chen1, *, Yupeng Deng1, Yu Meng1, Jiansheng Chen1, Chenhong Sui3, authorsList=Jianquan Zhou, Jingbo Chen, Yupeng Deng, Yu Meng, Jiansheng Chen, Chenhong Sui, authorCompany=null, correspAuthors=Jingbo Chen, 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=1322963026135089348, articleId=1322963022628651188, tenantId=1146029695717560320, journalId=1249024232475115590, language=CN, title=高分辨率多时相遥感变化检测数据集构建与验证, columnId=1322961445683601414, journalTitle=中国图象图形学报, columnName=数据集, runingTitle=null, highlight=null, articleAbstract=
目的

遥感变化检测是获取地表变化信息的核心手段。现有研究多基于双时相影像进行变化识别,难以准确捕捉长期、阶段性及多尺度的地表演化特征。探索多时相变化检测以刻画地表演化过程的动态变化已成为重要发展方向。然而,高分辨率、高质量且涵盖多类型地表变化的多时相遥感变化检测数据集仍然匮乏。针对这一问题,本文构建了一个覆盖中国五大典型区域——长三角、珠三角、京津冀、成渝及西北地区的高分辨率、多时相遥感变化检测数据集HR-MTCD(high-resolution multi-temporal change detection)。

方法

数据集包括时间跨度5年,共1 601组8 005幅分辨率约0.5 m的遥感影像及变化标签,覆盖区域包含平原、丘陵、山地及高原等多样地理环境,重点聚焦建筑物新增与拆除、大面积植被变化等典型地表变化类型,兼顾城市扩张与生态环境演变,为多类型地表变化研究及多时相变化检测算法提供数据支撑。

结果

在多种主流变化检测模型上的实验表明,HR-MTCD数据集可用于验证不同模型在场景复杂性、变化类型多样性与时序跨度方面的性能。同时,在统一实验框架下构建的递进式跨时相扩展实验表明时间维度信息在变化检测中具有重要价值。

结论

该数据集的构建为遥感变化检测从离散双时相变化识别向多时相地表变化过程刻画提供了重要数据基础。数据集可通过以下链接获取:https://doi.org/10.57760/sciencedb.j00240.00110。

, authors=周建泉1, 2, 陈静波1, *, 邓毓弸1, 孟瑜1, 陈建胜1, 隋晨红3, authorsList=周建泉, 陈静波, 邓毓弸, 孟瑜, 陈建胜, 隋晨红, authorCompany=null, correspAuthors=陈静波, authorNote=

周建泉,男,硕士研究生,主要研究方向为高分辨率遥感变化检测。E-mail:

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:

邓毓弸,男,特别研究助理,主要研究方向为遥感要素结构化标识与遥感图像变化检测。E-mail:

孟瑜,女,研究员,主要研究方向为跨域数据智能处理。E-mail:

陈建胜,男,高级工程师,主要研究方向为遥感图像智能解译和数据治理。E-mail:

隋晨红,女,副教授,主要研究方向为多模态遥感信息处理和对抗攻防。E-mail:

, correspAuthorsNote=
陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=bzwPJjKkvao/Ef2DxGavCQ==, magXml=2hg8Sf39IHUCbPKIzkmJAA==, pdfUrl=null, pdf=ebouQGnrycuxEFtdFj5yJQ==, pdfFileSize=35703785, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=U/9NyRmyuI8hZ7OHtlNkCA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=sJ2p4KrqyGuVtKTMBt40hw==, mapNumber=null, fund=null)}, authors=[Author(id=1322963026596462799, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhoujianquan23@mails.ucas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963026680348882, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026596462799, language=EN, stringName=Jianquan Zhou, firstName=Jianquan, middleName=null, lastName=Zhou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China
2 School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963026751652051, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026596462799, language=CN, stringName=周建泉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 中国科学院空天信息创新研究院,北京 100094
2 中国科学院大学电子电气与通信工程学院,北京 100049, bio={"content":"

周建泉,男,硕士研究生,主要研究方向为高分辨率遥感变化检测。E-mail:

"}, bioImg=null, bioContent=

周建泉,男,硕士研究生,主要研究方向为高分辨率遥感变化检测。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)]), AuthorCompany(id=1322963026437079240, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=2, ext=[AuthorCompanyExt(id=1322963026445467849, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026437079240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China), AuthorCompanyExt(id=1322963026449662154, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026437079240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国科学院大学电子电气与通信工程学院,北京 100049)])]), Author(id=1322963026848121045, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenjb@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322963026923618519, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026848121045, language=EN, stringName=Jingbo Chen, firstName=Jingbo, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963027011698904, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026848121045, language=CN, stringName=陈静波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:

"}, bioImg=null, bioContent=

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963027091390682, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dengyp@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963027175276764, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027091390682, language=EN, stringName=Yupeng Deng, firstName=Yupeng, middleName=null, lastName=Deng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963027238191325, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027091390682, language=CN, stringName=邓毓弸, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

邓毓弸,男,特别研究助理,主要研究方向为遥感要素结构化标识与遥感图像变化检测。E-mail:

"}, bioImg=null, bioContent=

邓毓弸,男,特别研究助理,主要研究方向为遥感要素结构化标识与遥感图像变化检测。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963027301105887, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=mengyu@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963027359826145, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027301105887, language=EN, stringName=Yu Meng, firstName=Yu, middleName=null, lastName=Meng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963027422740706, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027301105887, language=CN, stringName=孟瑜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

孟瑜,女,研究员,主要研究方向为跨域数据智能处理。E-mail:

"}, bioImg=null, bioContent=

孟瑜,女,研究员,主要研究方向为跨域数据智能处理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963029075296484, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenjs@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963029171765478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029075296484, language=EN, stringName=Jiansheng Chen, firstName=Jiansheng, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963029243068647, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029075296484, language=CN, stringName=陈建胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

陈建胜,男,高级工程师,主要研究方向为遥感图像智能解译和数据治理。E-mail:

"}, bioImg=null, bioContent=

陈建胜,男,高级工程师,主要研究方向为遥感图像智能解译和数据治理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963029305983209, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sui6662015@ytu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963029373092075, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029305983209, language=EN, stringName=Chenhong Sui, firstName=Chenhong, middleName=null, lastName=Sui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 School of Physics and Electronic Information,Yantai University,Yantai 264005,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963029440200940, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029305983209, language=CN, stringName=隋晨红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 烟台大学物理与电子信息学院,烟台 264005, bio={"content":"

隋晨红,女,副教授,主要研究方向为多模态遥感信息处理和对抗攻防。E-mail:

"}, bioImg=null, bioContent=

隋晨红,女,副教授,主要研究方向为多模态遥感信息处理和对抗攻防。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026508382411, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=3, ext=[AuthorCompanyExt(id=1322963026520965324, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026508382411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Physics and Electronic Information,Yantai University,Yantai 264005,China), AuthorCompanyExt(id=1322963026529353933, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026508382411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 烟台大学物理与电子信息学院,烟台 264005)])])], keywords=[Keyword(id=1322963029528281325, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, orderNo=1, keyword=remote sensing change detection(RSCD)), Keyword(id=1322963029587001582, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, orderNo=2, keyword=multi-temporal high-resolution dataset), Keyword(id=1322963029641527535, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, orderNo=3, keyword=urban expansion monitoring), Keyword(id=1322963029704442096, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, orderNo=4, keyword=ecological evolution analysis), Keyword(id=1322963029784133873, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, orderNo=5, keyword=temporal land surface dynamics), Keyword(id=1322963029842854130, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, orderNo=1, keyword=遥感变化检测(RSCD)), Keyword(id=1322963029914157299, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, orderNo=2, keyword=多时相高分辨率数据集), Keyword(id=1322963029993849076, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, orderNo=3, keyword=城市扩张监测), Keyword(id=1322963030060957941, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, orderNo=4, keyword=生态演变分析), Keyword(id=1322963030123872502, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, orderNo=5, keyword=时序地表动态)], refs=[Reference(id=1322963033953272081, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=207, pageEnd=210, url=null, language=null, rfNumber=null, rfOrder=0, authorNames=Bandara W G C, Patel V M, journalName=IGARSS 2022—2022 IEEE International Geoscience and Remote Sensing Symposium, refType=null, unstructuredReference=Bandara W G C and Patel V M. 2022. A transformer-based Siamese network for change detection//IGARSS 2022—2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur,Malaysia: IEEE: 207-210 [DOI: 10.1109/IGARSS46834.2022.9883686], articleTitle=A transformer-based Siamese network for change detection, refAbstract=null), Reference(id=1322963034032963858, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2000, volume=38, issue=3, pageStart=1171, pageEnd=1182, url=null, language=null, rfNumber=null, rfOrder=1, authorNames=Bruzzone L, Prieto D F, journalName=IEEE Transactions on Geoscience and Remote sensing, refType=null, unstructuredReference=Bruzzone L and Prieto D F. 2000. Automatic analysis of the difference image for unsupervised change detection. IEEE Transactions on Geoscience and Remote sensing,38(3): 1171-1182 [DOI: 10.1109/36.843009], articleTitle=Automatic analysis of the difference image for unsupervised change detection, refAbstract=null), Reference(id=1322963034095878419, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=4063, pageEnd=4067, url=null, language=null, rfNumber=null, rfOrder=2, authorNames=Caye Daudt R, Le Saux B, Boulch A, journalName=null, refType=null, unstructuredReference=Caye Daudt R,Le Saux B and Boulch A. 2018. Fully convolutional Siamese networks for change detection//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens,Greece: IEEE: 4063-4067 [DOI: 10.1109/ICIP.2018.8451652], articleTitle=Fully convolutional Siamese networks for change detection, refAbstract=null), Reference(id=1322963034183958804, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=null, pageEnd=5607514, url=null, language=null, rfNumber=null, rfOrder=3, authorNames=Chen H, Qi Z P, Shi Z W, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Chen H,Qi Z P and Shi Z W. 2022. Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing,60: #5607514 [DOI: 10.1109/TGRS.2021.3095166], articleTitle=Remote sensing image change detection with transformers, refAbstract=null), Reference(id=1322963034263650581, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=10, pageStart=null, pageEnd=1662, url=null, language=null, rfNumber=null, rfOrder=4, authorNames=Chen H, Shi Z W, journalName=Remote Sensing, refType=null, unstructuredReference=Chen H and Shi Z W. 2020. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing,12(10): #1662 [DOI: 10.3390/rs12101662], articleTitle=A spatial-temporal attention-based method and a new dataset for remote sensing image change detection, refAbstract=null), Reference(id=1322963034330759446, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=8581, pageEnd=8584, url=null, language=null, rfNumber=null, rfOrder=5, authorNames=Chen K Y, Liu C Y, Li W Y, Liu Z L, Chen H, Zhang H T, journalName=IGARSS 2024—2024 IEEE International Geoscience and Remote Sensing Symposium, refType=null, unstructuredReference=Chen K Y,Liu C Y,Li W Y,Liu Z L,Chen H,Zhang H T,et al. 2024. Time travelling pixels: bitemporal features integration with foundation model for remote sensing image change detection//IGARSS 2024—2024 IEEE International Geoscience and Remote Sensing Symposium. Athens,Greece: IEEE: 8581-8584 [DOI: 10.1109/IGARSS53475.2024.10640593], articleTitle=Time travelling pixels: bitemporal features integration with foundation model for remote sensing image change detection, refAbstract=null), Reference(id=1322963034406256919, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=87, issue=3, pageStart=2101, pageEnd=2123, url=null, language=null, rfNumber=null, rfOrder=6, authorNames=Das S, Angadi D P, journalName=GeoJournal, refType=null, unstructuredReference=Das S and Angadi D P. 2022. Land use land cover change detection and monitoring of urban growth using remote sensing and GIS techniques: a micro-level study. GeoJournal,87(3): 2101-2123 [DOI: 10.1007/s10708-020-10359-1], articleTitle=Land use land cover change detection and monitoring of urban growth using remote sensing and GIS techniques: a micro-level study, refAbstract=null), Reference(id=1322963034469171480, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2008, volume=29, issue=16, pageStart=4823, pageEnd=4838, url=null, language=null, rfNumber=null, rfOrder=7, authorNames=Deng J S, Wang K, Deng Y H, Qi G J, journalName=International Journal of Remote Sensing, refType=null, unstructuredReference=Deng J S,Wang K,Deng Y H and Qi G J. 2008. PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite data. International Journal of Remote Sensing,29(16): 4823-4838 [DOI: 10.1080/01431160801950162], articleTitle=PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite data, refAbstract=null), Reference(id=1322963034536280345, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2020, volume=161, issue=null, pageStart=278, pageEnd=293, url=null, language=null, rfNumber=null, rfOrder=8, authorNames=Du P J, Wang X, Chen D M, Liu S C, Lin C, Meng Y P, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference=Du P J,Wang X,Chen D M,Liu S C,Lin C and Meng Y P. 2020. An improved change detection approach using tri-temporal logic-verified change vector analysis. ISPRS Journal of Photogrammetry and Remote Sensing,161: 278-293 [DOI: 10.1016/j.isprsjprs.2020.01.026], articleTitle=An improved change detection approach using tri-temporal logic-verified change vector analysis, refAbstract=null), Reference(id=1322963034603389210, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2023, volume=61, issue=null, pageStart=null, pageEnd=5610111, url=null, language=null, rfNumber=null, rfOrder=9, authorNames=Fang S, Li K Y, Li Z, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Fang S,Li K Y and Li Z. 2023. Changer: feature interaction is what you need for change detection. IEEE Transactions on Geoscience and Remote Sensing,61: #5610111 [DOI: 10.1109/TGRS.2023.3277496], articleTitle=Changer: feature interaction is what you need for change detection, refAbstract=null), Reference(id=1322963034674692379, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=19, issue=null, pageStart=null, pageEnd=8007805, url=null, language=null, rfNumber=null, rfOrder=10, authorNames=Fang S, Li K Y, Shao J Y, Li Z, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Fang S,Li K Y,Shao J Y and Li Z. 2022. SNUNet-CD: a densely connected Siamese network for change detection of VHR images. IEEE Geoscience and Remote Sensing Letters,19: #8007805 [DOI: 10.1109/LGRS.2021.3056416], articleTitle=SNUNet-CD: a densely connected Siamese network for change detection of VHR images, refAbstract=null), Reference(id=1322963034750189852, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2019, volume=16, issue=10, pageStart=1655, pageEnd=1659, url=null, language=null, rfNumber=null, rfOrder=11, authorNames=Gao Y H, Gao F, Dong J Y, Wang S K, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Gao Y H,Gao F,Dong J Y and Wang S K. 2019. Transferred deep learning for sea ice change detection from synthetic-aperture radar images. IEEE Geoscience and Remote Sensing Letters,16(10): 1655-1659 [DOI: 10.1109/LGRS.2019.2906279], articleTitle=Transferred deep learning for sea ice change detection from synthetic-aperture radar images, refAbstract=null), Reference(id=1322963034850853149, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2023, volume=16, issue=null, pageStart=3867, pageEnd=3878, url=null, language=null, rfNumber=null, rfOrder=12, authorNames=Han C X, Wu C, Guo H N, Hu M Q, Chen H R X, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Han C X,Wu C,Guo H N,Hu M Q and Chen H R X. 2023. HANet: a hierarchical attention network for change detection with bitemporal very-high-resolution remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,16: 3867-3878 [DOI: 10.1109/JSTARS.2023.3264802], articleTitle=HANet: a hierarchical attention network for change detection with bitemporal very-high-resolution remote sensing images, refAbstract=null), Reference(id=1322963034922156318, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=2725, pageEnd=2729, url=null, language=null, rfNumber=null, rfOrder=13, authorNames=Ji D Y, Gao S Q, Tao M Y, Lu H T, Zhao F, journalName=null, refType=null, unstructuredReference=Ji D Y,Gao S Q,Tao M Y,Lu H T and Zhao F. 2024. Changenet: multi-temporal asymmetric change detection dataset//Proceedings of 2024 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Seoul,Korea(South): IEEE: 2725-2729 [DOI: 10.1109/ICASSP48485.2024.10446592], articleTitle=Changenet: multi-temporal asymmetric change detection dataset, refAbstract=null), Reference(id=1322963034993459487, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2019, volume=57, issue=1, pageStart=574, pageEnd=586, url=null, language=null, rfNumber=null, rfOrder=14, authorNames=Ji S P, Wei S Q, Lu M, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Ji S P,Wei S Q and Lu M. 2019. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing,57(1): 574-586 [DOI: 10.1109/TGRS.2018.2858817], articleTitle=Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set, refAbstract=null), Reference(id=1322963035089928480, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2024, volume=62, issue=null, pageStart=null, pageEnd=5610112, url=null, language=null, rfNumber=null, rfOrder=15, authorNames=Li K Y, Cao X Y, Meng D Y, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Li K Y,Cao X Y and Meng D Y. 2024. A new learning paradigm for foundation model-based remote-sensing change detection. IEEE Transactions on Geoscience and Remote Sensing,62: #5610112 [DOI: 10.1109/TGRS.2024.3365825], articleTitle=A new learning paradigm for foundation model-based remote-sensing change detection, refAbstract=null), Reference(id=1322963035224146209, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=null, pageEnd=5622519, url=null, language=null, rfNumber=null, rfOrder=16, authorNames=Li Q Y, Zhong R F, Du X, Du Y, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Li Q Y,Zhong R F,Du X and Du Y. 2022. TransUNetCD: a hybrid transformer network for change detection in optical remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing,60: #5622519 [DOI: 10.1109/TGRS.2022.3169479], articleTitle=TransUNetCD: a hybrid transformer network for change detection in optical remote-sensing images, refAbstract=null), Reference(id=1322963035320615202, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=15, issue=null, pageStart=4297, pageEnd=4306, url=null, language=null, rfNumber=null, rfOrder=17, authorNames=Liu M X, Chai Z Q, Deng H J, Liu R, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Liu M X,Chai Z Q,Deng H J and Liu R. 2022. A CNN-transformer network with multiscale context aggregation for fine-grained cropland change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,15: 4297-4306 [DOI: 10.1109/JSTARS.2022.3177235], articleTitle=A CNN-transformer network with multiscale context aggregation for fine-grained cropland change detection, refAbstract=null), Reference(id=1322963035572273443, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2018, volume=10, issue=3, pageStart=null, pageEnd=471, url=null, language=null, rfNumber=null, rfOrder=18, authorNames=Lyu H B, Lu H, Mou L C, Li W Y, Wright J, Li X C, journalName=Remote Sensing, refType=null, unstructuredReference=Lyu H B,Lu H,Mou L C,Li W Y,Wright J,Li X C,et al. 2018. Long-term annual mapping of four cities on different continents by applying a deep information learning method to Landsat data. Remote Sensing,10(3): #471 [DOI: 10.3390/rs10030471], articleTitle=Long-term annual mapping of four cities on different continents by applying a deep information learning method to Landsat data, refAbstract=null), Reference(id=1322963035656159524, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2024, volume=62, issue=null, pageStart=null, pageEnd=4404912, url=null, language=null, rfNumber=null, rfOrder=19, authorNames=Lyu Z Y, Lei Z J, Xie L F, Falco N, Shi C, You Z Z, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Lyu Z Y,Lei Z J,Xie L F,Falco N,Shi C and You Z Z. 2024. Novel distribution distance based on inconsistent adaptive region for change detection using hyperspectral remote sensing images. IEEE Transactions on Geoscience and Remote Sensing,62: #4404912 [DOI: 10.1109/TGRS.2024.3378526], articleTitle=Novel distribution distance based on inconsistent adaptive region for change detection using hyperspectral remote sensing images, refAbstract=null), Reference(id=1322963035719074085, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2023, volume=66, issue=4, pageStart=null, pageEnd=140306, url=null, language=null, rfNumber=null, rfOrder=20, authorNames=Pang C, Wu J, Ding J, Song C, Xia G S, journalName=Science China Information Sciences, refType=null, unstructuredReference=Pang C,Wu J,Ding J,Song C and Xia G S. 2023. Detecting building changes with off-nadir aerial images. Science China Information Sciences,66(4): #140306 [DOI: 10.1007/s11432-022-3691-4], articleTitle=Detecting building changes with off-nadir aerial images, refAbstract=null), Reference(id=1322963035786182950, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=336, pageEnd=344, url=null, language=null, rfNumber=null, rfOrder=21, authorNames=Saha S, Bovolo F, Bruzzone L, journalName=Proceedings of SPIE 10789, refType=null, unstructuredReference=Saha S,Bovolo F and Bruzzone L. 2018. Destroyed-buildings detection from VHR SAR images using deep features//Proceedings of SPIE 10789,Image and Signal Processing for Remote Sensing XXIV. Berlin,Germany: SPIE: 336-344 [DOI: 10.1117/12.2325149], articleTitle=Destroyed-buildings detection from VHR SAR images using deep features, refAbstract=null), Reference(id=1322963035853291815, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2013, volume=128, issue=null, pageStart=246, pageEnd=258, url=null, language=null, rfNumber=null, rfOrder=22, authorNames=Sexton J O, Urban D L, Donohue M J, Song C H, journalName=Remote Sensing of Environment, refType=null, unstructuredReference=Sexton J O,Urban D L,Donohue M J and Song C H. 2013. Long-term land cover dynamics by multi-temporal classification across the Landsat-5 record. Remote Sensing of Environment,128: 246-258 [DOI: 10.1016/j.rse.2012.10.010], articleTitle=Long-term land cover dynamics by multi-temporal classification across the Landsat-5 record, refAbstract=null), Reference(id=1322963035941372200, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2021, volume=13, issue=24, pageStart=null, pageEnd=5094, url=null, language=null, rfNumber=null, rfOrder=23, authorNames=Shen L, Lu Y, Chen H, Wei H, Xie D H, Yue J B, journalName=Remote Sensing, refType=null, unstructuredReference=Shen L,Lu Y,Chen H,Wei H,Xie D H,Yue J B,et al. 2021. S2Looking: a satellite side-looking dataset for building change detection. Remote Sensing,13(24): #5094 [DOI: 10.3390/rs13245094], articleTitle=S2Looking: a satellite side-looking dataset for building change detection, refAbstract=null), Reference(id=1322963036004286761, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=null, pageEnd=5604816, url=null, language=null, rfNumber=null, rfOrder=24, authorNames=Shi Q, Liu M X, Li S C, Liu X P, Wang F, Zhang L P, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Shi Q,Liu M X,Li S C,Liu X P,Wang F and Zhang L P. 2022. A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection. IEEE Transactions on Geoscience and Remote Sensing,60: #5604816 [DOI: 10.1109/TGRS.2021.3085870], articleTitle=A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection, refAbstract=null), Reference(id=1322963036079784234, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=1989, volume=10, issue=6, pageStart=989, pageEnd=1003, url=null, language=null, rfNumber=null, rfOrder=25, authorNames=Singh A, journalName=International Journal of Remote Sensing, refType=null, unstructuredReference=Singh A. 1989. Review article digital change detection techniques using remotely-sensed data. International Journal of Remote Sensing,10(6): 989-1003 [DOI: 10.1080/01431168908903939], articleTitle=Review article digital change detection techniques using remotely-sensed data, refAbstract=null), Reference(id=1322963036151087403, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=216, pageEnd=232, url=null, language=null, rfNumber=null, rfOrder=26, authorNames=Van Etten A and Hogan D, journalName=Proceedings of the NeurIPS 2020 Competition and Demonstration Track, refType=null, unstructuredReference=Van Etten A and Hogan D. 2021. The SpaceNet multi-temporal urban development challenge//Proceedings of the NeurIPS 2020 Competition and Demonstration Track. Vancouver,Canada: PMLR: 216-232, articleTitle=The SpaceNet multi-temporal urban development challenge, refAbstract=null), Reference(id=1322963036239167788, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=3, pageStart=870, pageEnd=882, url=null, language=null, rfNumber=null, rfOrder=27, authorNames=Wang R F, Yang Z J, Qiu H, Wang F, Gao G, Wu D, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Wang R F,Yang Z J,Qiu H,Wang F,Gao G and Wu D. 2025. Lightweight change detection network integrating feature interaction and fusion. Journal of Image and Graphics,30(3): 870-882, articleTitle=Lightweight change detection network integrating feature interaction and fusion, refAbstract=null), Reference(id=1322963036297888045, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2025, volume=30, issue=3, pageStart=870, pageEnd=882, url=null, language=null, rfNumber=null, rfOrder=28, authorNames=王仁芳, 杨梓健, 邱虹, 王峰, 高广, 吴敦, journalName=中国图象图形学报, refType=null, unstructuredReference=王仁芳,杨梓健,邱虹,王峰,高广,吴敦. 2025. 结合特征交互和融合的轻量级变化检测网络. 中国图象图形学报,30(3): 870-882 [DOI: 10.11834/jig.240280], articleTitle=结合特征交互和融合的轻量级变化检测网络, refAbstract=null), Reference(id=1322963036381774126, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2020, volume=25, issue=6, pageStart=1271, pageEnd=1282, url=null, language=null, rfNumber=null, rfOrder=29, authorNames=Wang Y H, Gao L R, Chen Z C, Zhang B, journalName=Journal of Image and Graphics, refType=null, unstructuredReference=Wang Y H,Gao L R,Chen Z C and Zhang B. 2020. Deep learning and superpixel-based method for high-resolution remote sensing image change detection. Journal of Image and Graphics,25(6): 1271-1282, articleTitle=Deep learning and superpixel-based method for high-resolution remote sensing image change detection, refAbstract=null), Reference(id=1322963036457271599, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2020, volume=25, issue=6, pageStart=1271, pageEnd=1282, url=null, language=null, rfNumber=null, rfOrder=30, authorNames=王艳恒, 高连如, 陈正超, 张兵, journalName=中国图象图形学报, refType=null, unstructuredReference=王艳恒,高连如,陈正超,张兵. 2020. 结合深度学习和超像元的高分遥感影像变化检测. 中国图象图形学报,25(6): 1271-1282 [DOI: 10.11834/jig.190319], articleTitle=结合深度学习和超像元的高分遥感影像变化检测, refAbstract=null), Reference(id=1322963038109827376, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=1977, volume=43, issue=12, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=null, rfOrder=31, authorNames=Weismiller R A, Kristof S J, Scholz D K, Anuta P E, Momin S A, journalName=Photogrammetric Engineering and Remote Sensing, refType=null, unstructuredReference=Weismiller R A,Kristof S J,Scholz D K,Anuta P E and Momin S A. 1977. Change detection in coastal zone environments. Photogrammetric Engineering and Remote Sensing,43(12), articleTitle=Change detection in coastal zone environments, refAbstract=null), Reference(id=1322963038181130545, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/pdf/2010.05687.pdf, language=null, rfNumber=null, rfOrder=32, authorNames=Yang K P, Xia G S, Liu Z C, Du B, Yang W, Pelillo M, journalName=null, refType=null, unstructuredReference=Yang K P,Xia G S,Liu Z C,Du B,Yang W,Pelillo M,et al. 2020. Semantic change detection with asymmetric Siamese networks [2025-11-14]. [EB/OL]., articleTitle=Semantic change detection with asymmetric Siamese networks, refAbstract=null), Reference(id=1322963038252433714, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=null, pageEnd=5224713, url=null, language=null, rfNumber=null, rfOrder=33, authorNames=Zhang C, Wang L J, Cheng S L, Li Y M, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Zhang C,Wang L J,Cheng S L and Li Y M. 2022. SwinSUNet: pure transformer network for remote sensing image change detection. IEEE Transactions on Geoscience and Remote Sensing,60: #5224713 [DOI: 10.1109/TGRS.2022.3160007], articleTitle=SwinSUNet: pure transformer network for remote sensing image change detection, refAbstract=null), Reference(id=1322963038327931187, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2020, volume=166, issue=null, pageStart=183, pageEnd=200, url=null, language=null, rfNumber=null, rfOrder=34, authorNames=Zhang C X, Yue P, Tapete D, Jiang L C, Shangguan B Y, Huang L, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference=Zhang C X,Yue P,Tapete D,Jiang L C,Shangguan B Y,Huang L,et al. 2020. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing,166: 183-200 [DOI: 10.1016/j.isprsjprs.2020.06.003], articleTitle=A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images, refAbstract=null), Reference(id=1322963038407622964, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2024, volume=62, issue=null, pageStart=null, pageEnd=4402218, url=null, language=null, rfNumber=null, rfOrder=35, authorNames=Zhang H, Liu W, Niu H, Yin P C, Dong S L, Wu J L, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Zhang H,Liu W,Niu H,Yin P C,Dong S L,Wu J L,et al. 2024. Land cover change detection based on vector polygons and deep learning with high-resolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing,62: #4402218 [DOI: 10.1109/TGRS.2023.3346968], articleTitle=Land cover change detection based on vector polygons and deep learning with high-resolution remote sensing images, refAbstract=null), Reference(id=1322963038499897653, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2024, volume=17, issue=null, pageStart=19601, pageEnd=19615, url=null, language=null, rfNumber=null, rfOrder=36, authorNames=Zhao Y T, Li H C, Lei S, Liu N Q, Pan J, Celik T, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Zhao Y T,Li H C,Lei S,Liu N Q,Pan J and Celik T. 2024. COUD: continual urbanization detector for time series building change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,17: 19601-19615 [DOI: 10.1109/JSTARS.2024.3482559], articleTitle=COUD: continual urbanization detector for time series building change detection, refAbstract=null), Reference(id=1322963038562812214, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=24011, pageEnd=24022, url=null, language=null, rfNumber=null, rfOrder=37, authorNames=Zhu D W, Huang X H, Huang H Y, Zhou H, Shao Z F, journalName=null, refType=null, unstructuredReference=Zhu D W,Huang X H,Huang H Y,Zhou H and Shao Z F. 2025. Change3D: revisiting change detection and captioning from a video modeling perspective//Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville,USA: IEEE: 24011-24022 [DOI: 10.1109/CVPR52734.2025.02236], articleTitle=Change3D: revisiting change detection and captioning from a video modeling perspective, refAbstract=null), Reference(id=1322963038629921079, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, doi=null, pmid=null, pmcid=null, year=2022, volume=282, issue=null, pageStart=null, pageEnd=113266, url=null, language=null, rfNumber=null, rfOrder=38, authorNames=Zhu Z, Qiu S, Ye S, journalName=Remote Sensing of Environment, refType=null, unstructuredReference=Zhu Z,Qiu S and Ye S. 2022. Remote sensing of land change: a multifaceted perspective. Remote Sensing of Environment,282: #113266 [DOI: 10.1016/j.rse.2022.113266], articleTitle=Remote sensing of land change: a multifaceted perspective, refAbstract=null)], funds=[Fund(id=1322963033764528399, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, awardId=null, language=EN, fundingSource=Strategic Priority Research Program of the Chinese Academy of Sciences(XDA0360303), fundOrder=null, country=null), Fund(id=1322963033860997392, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, awardId=null, language=CN, fundingSource=中国科学院前瞻战略科技先导专项项目(XDA0360303), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)]), AuthorCompany(id=1322963026437079240, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=2, ext=[AuthorCompanyExt(id=1322963026445467849, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026437079240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China), AuthorCompanyExt(id=1322963026449662154, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026437079240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国科学院大学电子电气与通信工程学院,北京 100049)]), AuthorCompany(id=1322963026508382411, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=3, ext=[AuthorCompanyExt(id=1322963026520965324, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026508382411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Physics and Electronic Information,Yantai University,Yantai 264005,China), AuthorCompanyExt(id=1322963026529353933, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026508382411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 烟台大学物理与电子信息学院,烟台 264005)])], figs=[ArticleFig(id=1322963030241313015, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.1, caption=Illustration of the model-assisted annotation process ((a) model-predicted change regions;(b) manually revised reference labels), figureFileSmall=ck/4Ee7IwmvbwNqulXDvZQ==, figureFileBig=U/9NyRmyuI8hZ7OHtlNkCA==, tableContent=null), ArticleFig(id=1322963030304227576, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图1, caption=模型辅助标注过程示意图, figureFileSmall=ck/4Ee7IwmvbwNqulXDvZQ==, figureFileBig=U/9NyRmyuI8hZ7OHtlNkCA==, tableContent=null), ArticleFig(id=1322963030530719993, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.2, caption=Schematic diagram of dataset annotation and quality control process, figureFileSmall=7E1oLw34KC0IE6twqCTG/g==, figureFileBig=cuZ0XImhBVnMzykmlcQeiA==, tableContent=null), ArticleFig(id=1322963030589440250, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图2, caption=数据集标注与质控流程示意图, figureFileSmall=7E1oLw34KC0IE6twqCTG/g==, figureFileBig=cuZ0XImhBVnMzykmlcQeiA==, tableContent=null), ArticleFig(id=1322963030656549115, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.3, caption=Representative samples from the dataset, figureFileSmall=yfIgdhkgSYMXS3WdhZSk8w==, figureFileBig=6V917LKjZ4qKlGKFz6NuXw==, tableContent=null), ArticleFig(id=1322963030732046588, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图3, caption=部分样本集展示, figureFileSmall=yfIgdhkgSYMXS3WdhZSk8w==, figureFileBig=6V917LKjZ4qKlGKFz6NuXw==, tableContent=null), ArticleFig(id=1322963030790766845, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.4, caption=Schematic diagram of cross-temporal image pair organization, figureFileSmall=Rn61pHlbQk71KrHdX0jLsw==, figureFileBig=Eaj1wJPVLJOciLlkdehtfw==, tableContent=null), ArticleFig(id=1322963030853681406, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图4, caption=跨时相影像对组织形式示意图, figureFileSmall=Rn61pHlbQk71KrHdX0jLsw==, figureFileBig=Eaj1wJPVLJOciLlkdehtfw==, tableContent=null), ArticleFig(id=1322963030912401663, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.5, caption=Visual comparison of different types of change detection models on two sample pairs (the first sample group), figureFileSmall=Y4vXxMgTQMog58Qnjd6Trw==, figureFileBig=RYJAN+WBLZLUhJ6KaYiKyQ==, tableContent=null), ArticleFig(id=1322963030971121920, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图5, caption=不同类型变化检测模型在两组样例的可视化表现(第1组), figureFileSmall=Y4vXxMgTQMog58Qnjd6Trw==, figureFileBig=RYJAN+WBLZLUhJ6KaYiKyQ==, tableContent=null), ArticleFig(id=1322963031029842177, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.5, caption=Visual comparison of different types of change detection models on two sample pairs (the second sample group), figureFileSmall=ZVFmI3Z2PksMcSQT/xHp4Q==, figureFileBig=SN5QPnuz5o/DwxCnJeamAg==, tableContent=null), ArticleFig(id=1322963031092756738, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图5, caption=不同类型变化检测模型在两组样例的可视化表现(第2组), figureFileSmall=ZVFmI3Z2PksMcSQT/xHp4Q==, figureFileBig=SN5QPnuz5o/DwxCnJeamAg==, tableContent=null), ArticleFig(id=1322963031180837123, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Fig.6, caption=Visualization of model performance evolution with increasing temporal span, figureFileSmall=a476EeOKAyGJ+ZrjoxWclg==, figureFileBig=YyLDORAYTaSUu/DOT/kbDw==, tableContent=null), ArticleFig(id=1322963031252140292, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=图6, caption=随时间跨度增加模型检测性能演化的可视化结果, figureFileSmall=a476EeOKAyGJ+ZrjoxWclg==, figureFileBig=YyLDORAYTaSUu/DOT/kbDw==, tableContent=null), ArticleFig(id=1322963031310860549, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Table 1, caption=Introduction to high-resolution optical remote sensing image change detection datasets, figureFileSmall=null, figureFileBig=null, tableContent=
数据集分辨率/m影像尺寸/像素关注变化时相数量特点
WHU-CD0.332 207 × 15 354建筑物2典型城市建筑变化,影像质量高
BANDON0.62 048 × 2 048建筑物2倾斜视角航拍图像中建筑物变化检测
LEVIR-CD0.51 024 × 1 024建筑物2专注于建筑物新增与拆除变化
S2Looking0.5~0.81 024 × 1 024建筑物2农村地区建筑物变化
CLCD0.5~2512 × 512耕地变化2适用于农林监测
SYSU-CD0.5256 × 256综合变化2专注于城市和沿海变化
DSIFN-CD0.5~1512 × 512综合变化2专注于城市变化,涵盖国内6个城市
SECOND0.3~5512 × 512综合变化2聚焦6类核心地表覆盖类型
TSCD0.5256 × 256建筑物4聚焦成都区域建筑物时序变化
ChangeNet0.31 900 × 1 200综合变化6提出多时相不对称变化基准
), ArticleFig(id=1322963031373775110, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=表1, caption=

高分辨率光学遥感影像变化检测数据集介绍

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集分辨率/m影像尺寸/像素关注变化时相数量特点
WHU-CD0.332 207 × 15 354建筑物2典型城市建筑变化,影像质量高
BANDON0.62 048 × 2 048建筑物2倾斜视角航拍图像中建筑物变化检测
LEVIR-CD0.51 024 × 1 024建筑物2专注于建筑物新增与拆除变化
S2Looking0.5~0.81 024 × 1 024建筑物2农村地区建筑物变化
CLCD0.5~2512 × 512耕地变化2适用于农林监测
SYSU-CD0.5256 × 256综合变化2专注于城市和沿海变化
DSIFN-CD0.5~1512 × 512综合变化2专注于城市变化,涵盖国内6个城市
SECOND0.3~5512 × 512综合变化2聚焦6类核心地表覆盖类型
TSCD0.5256 × 256建筑物4聚焦成都区域建筑物时序变化
ChangeNet0.31 900 × 1 200综合变化6提出多时相不对称变化基准
), ArticleFig(id=1322963031466049799, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Table 2, caption=Statistical summary of sample sizes by region, figureFileSmall=null, figureFileBig=null, tableContent=
区域组数/组影像数量/幅
总计1 6018 005
珠三角地区2281 140
京津冀地区2351 175
长三角地区2541 270
西北地区2851 425
成渝地区5992 995
), ArticleFig(id=1322963031549935880, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=表2, caption=

各区域样本数量统计

, figureFileSmall=null, figureFileBig=null, tableContent=
区域组数/组影像数量/幅
总计1 6018 005
珠三角地区2281 140
京津冀地区2351 175
长三角地区2541 270
西北地区2851 425
成渝地区5992 995
), ArticleFig(id=1322963031612850441, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Table 3, caption=Results of different change detection methods, figureFileSmall=null, figureFileBig=null, tableContent=
类别模型骨干网络F1-score精确率召回率IoU
CNNTinyCD_v2TinyNet(B)49.6384.4235.1433.00
TinyNet(L)55.8077.9943.4438.69
HANETHAN44.4473.1231.9228.57
DSIFNVGG1664.8575.1557.0447.99
TransformerChangeStarResNet1852.4374.4040.4735.52
ResNet5053.9967.6844.9036.97
ChangerResNet1857.9577.9546.1240.80
ResNet5059.9175.1249.8242.76
ChangeFormerMiT_b065.2179.8955.0948.38
MiT_b162.8679.0952.1645.84
CNN-TransformerBITResNet1852.9377.8940.0835.99
ResNet5058.0574.1847.6840.89
基础模型BANCLIP_ViT_Base_Patch1663.6774.8655.3946.70
TTPVIT_SAM_L73.5275.1671.9458.12
), ArticleFig(id=1322963031684153610, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=表3, caption=

各类变化检测模型方法结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
类别模型骨干网络F1-score精确率召回率IoU
CNNTinyCD_v2TinyNet(B)49.6384.4235.1433.00
TinyNet(L)55.8077.9943.4438.69
HANETHAN44.4473.1231.9228.57
DSIFNVGG1664.8575.1557.0447.99
TransformerChangeStarResNet1852.4374.4040.4735.52
ResNet5053.9967.6844.9036.97
ChangerResNet1857.9577.9546.1240.80
ResNet5059.9175.1249.8242.76
ChangeFormerMiT_b065.2179.8955.0948.38
MiT_b162.8679.0952.1645.84
CNN-TransformerBITResNet1852.9377.8940.0835.99
ResNet5058.0574.1847.6840.89
基础模型BANCLIP_ViT_Base_Patch1663.6774.8655.3946.70
TTPVIT_SAM_L73.5275.1671.9458.12
), ArticleFig(id=1322963031772233995, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Table 4, caption=Comparison of generalization performance of different change detection models on cross-region testsets, figureFileSmall=null, figureFileBig=null, tableContent=
类别模型骨干网络F1-score精确率召回率IoU
CNNTinyCD_v2TinyNet (B)55.7373.6444.8338.63
TinyNet (L)60.7174.3351.3143.59
HANETHAN50.1262.1841.9833.44
DSIFNVGG1663.9274.2856.0946.97
TransformerChangeStarResNet1853.8563.8846.5536.85
ResNet5057.4767.7749.9040.32
ChangerResNet1861.5478.7250.5244.45
ResNet5061.8471.5954.4444.76
ChangeFormerMiT_b065.6178.3056.4748.83
MiT_b165.1980.8654.6048.35
CNN-TransformerBITResNet1855.6977.4543.4838.59
ResNet5061.9273.7053.3844.84
基础模型BANCLIP_ViT_Base_Patch1663.4968.8458.9146.51
TTPVIT_SAM_L74.8075.2474.3659.74
), ArticleFig(id=1322963031860314380, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=表4, caption=

各类变化检测模型在跨区域测试集上的泛化性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
类别模型骨干网络F1-score精确率召回率IoU
CNNTinyCD_v2TinyNet (B)55.7373.6444.8338.63
TinyNet (L)60.7174.3351.3143.59
HANETHAN50.1262.1841.9833.44
DSIFNVGG1663.9274.2856.0946.97
TransformerChangeStarResNet1853.8563.8846.5536.85
ResNet5057.4767.7749.9040.32
ChangerResNet1861.5478.7250.5244.45
ResNet5061.8471.5954.4444.76
ChangeFormerMiT_b065.6178.3056.4748.83
MiT_b165.1980.8654.6048.35
CNN-TransformerBITResNet1855.6977.4543.4838.59
ResNet5061.9273.7053.3844.84
基础模型BANCLIP_ViT_Base_Patch1663.4968.8458.9146.51
TTPVIT_SAM_L74.8075.2474.3659.74
), ArticleFig(id=1322963031948394765, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=EN, label=Table 5, caption=The validity of multi-temporal data, figureFileSmall=null, figureFileBig=null, tableContent=
模型时间跨度F1-score精确率召回率IoU
TinyCD_v21年55.8077.9943.4438.69
2年57.7977.5046.0840.64
3年61.2870.3354.344.18
4年62.7675.0953.9145.73
ChangeFormer1年62.8679.0952.1645.84
2年66.3981.1856.1549.68
3年67.2176.0560.2150.61
4年65.7477.7656.9348.96
BIT1年52.9377.8940.0835.99
2年55.8975.4344.438.79
3年54.4174.3242.9137.37
4年55.5276.2943.6438.43
), ArticleFig(id=1322963033651282190, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, language=CN, label=表5, caption=

多时相数据的有效性

, figureFileSmall=null, figureFileBig=null, tableContent=
模型时间跨度F1-score精确率召回率IoU
TinyCD_v21年55.8077.9943.4438.69
2年57.7977.5046.0840.64
3年61.2870.3354.344.18
4年62.7675.0953.9145.73
ChangeFormer1年62.8679.0952.1645.84
2年66.3981.1856.1549.68
3年67.2176.0560.2150.61
4年65.7477.7656.9348.96
BIT1年52.9377.8940.0835.99
2年55.8975.4344.438.79
3年54.4174.3242.9137.37
4年55.5276.2943.6438.43
)], 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.250563, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/10.11834/jig.250563, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/PDF/10.11834/jig.250563, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgtxtxxb/EN/PDF/10.11834/jig.250563, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1792080000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
高分辨率多时相遥感变化检测数据集构建与验证
收藏切换
PDF下载
周建泉 1, 2 , 陈静波 1, * , 邓毓弸 1 , 孟瑜 1 , 陈建胜 1 , 隋晨红 3
中国图象图形学报 | 数据集 2026,31(10): 3572-3589
收起
收藏切换
中国图象图形学报 |数据集 2026 , 31 (10) : 3572 -3589
高分辨率多时相遥感变化检测数据集构建与验证
全屏
[Author(id=1322963026596462799, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhoujianquan23@mails.ucas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963026680348882, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026596462799, language=EN, stringName=Jianquan Zhou, firstName=Jianquan, middleName=null, lastName=Zhou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China
2 School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963026751652051, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026596462799, language=CN, stringName=周建泉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 中国科学院空天信息创新研究院,北京 100094
2 中国科学院大学电子电气与通信工程学院,北京 100049, bio={"content":"

周建泉,男,硕士研究生,主要研究方向为高分辨率遥感变化检测。E-mail:

"}, bioImg=null, bioContent=

周建泉,男,硕士研究生,主要研究方向为高分辨率遥感变化检测。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)]), AuthorCompany(id=1322963026437079240, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=2, ext=[AuthorCompanyExt(id=1322963026445467849, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026437079240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China), AuthorCompanyExt(id=1322963026449662154, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026437079240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国科学院大学电子电气与通信工程学院,北京 100049)])]), Author(id=1322963026848121045, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenjb@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322963026923618519, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026848121045, language=EN, stringName=Jingbo Chen, firstName=Jingbo, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963027011698904, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963026848121045, language=CN, stringName=陈静波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:

"}, bioImg=null, bioContent=

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963027091390682, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dengyp@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963027175276764, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027091390682, language=EN, stringName=Yupeng Deng, firstName=Yupeng, middleName=null, lastName=Deng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963027238191325, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027091390682, language=CN, stringName=邓毓弸, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

邓毓弸,男,特别研究助理,主要研究方向为遥感要素结构化标识与遥感图像变化检测。E-mail:

"}, bioImg=null, bioContent=

邓毓弸,男,特别研究助理,主要研究方向为遥感要素结构化标识与遥感图像变化检测。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963027301105887, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=mengyu@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963027359826145, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027301105887, language=EN, stringName=Yu Meng, firstName=Yu, middleName=null, lastName=Meng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963027422740706, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963027301105887, language=CN, stringName=孟瑜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

孟瑜,女,研究员,主要研究方向为跨域数据智能处理。E-mail:

"}, bioImg=null, bioContent=

孟瑜,女,研究员,主要研究方向为跨域数据智能处理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963029075296484, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenjs@aircas.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963029171765478, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029075296484, language=EN, stringName=Jiansheng Chen, firstName=Jiansheng, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963029243068647, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029075296484, language=CN, stringName=陈建胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国科学院空天信息创新研究院,北京 100094, bio={"content":"

陈建胜,男,高级工程师,主要研究方向为遥感图像智能解译和数据治理。E-mail:

"}, bioImg=null, bioContent=

陈建胜,男,高级工程师,主要研究方向为遥感图像智能解译和数据治理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026357387461, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=1, ext=[AuthorCompanyExt(id=1322963026365776070, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China), AuthorCompanyExt(id=1322963026374164679, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026357387461, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国科学院空天信息创新研究院,北京 100094)])]), Author(id=1322963029305983209, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sui6662015@ytu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322963029373092075, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029305983209, language=EN, stringName=Chenhong Sui, firstName=Chenhong, middleName=null, lastName=Sui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 School of Physics and Electronic Information,Yantai University,Yantai 264005,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322963029440200940, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, authorId=1322963029305983209, language=CN, stringName=隋晨红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 烟台大学物理与电子信息学院,烟台 264005, bio={"content":"

隋晨红,女,副教授,主要研究方向为多模态遥感信息处理和对抗攻防。E-mail:

"}, bioImg=null, bioContent=

隋晨红,女,副教授,主要研究方向为多模态遥感信息处理和对抗攻防。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322963026508382411, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, xref=3, ext=[AuthorCompanyExt(id=1322963026520965324, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026508382411, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Physics and Electronic Information,Yantai University,Yantai 264005,China), AuthorCompanyExt(id=1322963026529353933, tenantId=1146029695717560320, journalId=1249024232475115590, articleId=1322963022628651188, companyId=1322963026508382411, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 烟台大学物理与电子信息学院,烟台 264005)])])]
周建泉1, 2 , 陈静波1, * , 邓毓弸1 , 孟瑜1 , 陈建胜1 , 隋晨红3
作者信息
  • 1 中国科学院空天信息创新研究院,北京 100094
  • 2 中国科学院大学电子电气与通信工程学院,北京 100049
  • 3 烟台大学物理与电子信息学院,烟台 264005
通讯作者:
陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:
作者简介:

周建泉,男,硕士研究生,主要研究方向为高分辨率遥感变化检测。E-mail:

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:

邓毓弸,男,特别研究助理,主要研究方向为遥感要素结构化标识与遥感图像变化检测。E-mail:

孟瑜,女,研究员,主要研究方向为跨域数据智能处理。E-mail:

陈建胜,男,高级工程师,主要研究方向为遥感图像智能解译和数据治理。E-mail:

隋晨红,女,副教授,主要研究方向为多模态遥感信息处理和对抗攻防。E-mail:

Construction and validation of a high-resolution multitemporal remote sensing change detection dataset
Jianquan Zhou1, 2 , Jingbo Chen1, * , Yupeng Deng1 , Yu Meng1 , Jiansheng Chen1 , Chenhong Sui3
Affiliations
  • 1 Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China
  • 2 School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China
  • 3 School of Physics and Electronic Information,Yantai University,Yantai 264005,China
出版时间: 2026-10-16 doi: 10.11834/jig.250563
文章导航
收藏切换
目的

遥感变化检测是获取地表变化信息的核心手段。现有研究多基于双时相影像进行变化识别,难以准确捕捉长期、阶段性及多尺度的地表演化特征。探索多时相变化检测以刻画地表演化过程的动态变化已成为重要发展方向。然而,高分辨率、高质量且涵盖多类型地表变化的多时相遥感变化检测数据集仍然匮乏。针对这一问题,本文构建了一个覆盖中国五大典型区域——长三角、珠三角、京津冀、成渝及西北地区的高分辨率、多时相遥感变化检测数据集HR-MTCD(high-resolution multi-temporal change detection)。

方法

数据集包括时间跨度5年,共1 601组8 005幅分辨率约0.5 m的遥感影像及变化标签,覆盖区域包含平原、丘陵、山地及高原等多样地理环境,重点聚焦建筑物新增与拆除、大面积植被变化等典型地表变化类型,兼顾城市扩张与生态环境演变,为多类型地表变化研究及多时相变化检测算法提供数据支撑。

结果

在多种主流变化检测模型上的实验表明,HR-MTCD数据集可用于验证不同模型在场景复杂性、变化类型多样性与时序跨度方面的性能。同时,在统一实验框架下构建的递进式跨时相扩展实验表明时间维度信息在变化检测中具有重要价值。

结论

该数据集的构建为遥感变化检测从离散双时相变化识别向多时相地表变化过程刻画提供了重要数据基础。数据集可通过以下链接获取:https://doi.org/10.57760/sciencedb.j00240.00110。

遥感变化检测(RSCD)  /  多时相高分辨率数据集  /  城市扩张监测  /  生态演变分析  /  时序地表动态
Objective

The acquisition of land surface change information is a fundamental pathway for understanding the evolution of the natural environment and the impacts of human activities. Land surface changes reflect the joint influence of natural processes and anthropogenic drivers on landscape pattern evolution. Such changes are not only governed by natural factors but are also closely intertwined with social and economic development. Timely and accurate monitoring and identification of these changes are crucial for gaining deeper insights into regional ecological succession and urban expansion processes,and they provide essential scientific support for territorial spatial planning,ecological and environmental protection,and social governance. Remote sensing change detection is an important research direction in the fields of remote sensing and geographic information science,and it has attracted increasing attention in recent years. The core objective of remote sensing change detection is to identify considerable changes in land-cover elements within the same geographical area across different time points by analyzing bitemporal or multitemporal remote sensing imagery. Most existing studies focus on bitemporal change detection. Although substantial progress has been achieved in terms of detection accuracy and computational efficiency,bitemporal approaches remain inherently limited in their ability to model temporal dynamics. In real-world scenarios,land surface changes often exhibit continuity,stage-wise progression,and multiscale temporal characteristics. Typical examples include the gradual expansion of urban areas,seasonal degradation and recovery of vegetation,and nonlinear postdisaster land surface restoration processes. Relying solely on two temporal snapshots makes it difficult to characterize such long-term evolutionary trends and complex dynamic patterns,and it also limits the ability to uncover latent trends associated with gradual or periodic changes. Moreover,given that only two temporal images are involved,bitemporal approaches are more susceptible to pseudo changes and misclassification when confronted with illumination variations,observation noise,and other acquisition-related inconsistencies. Consequently,exploring multitemporal change detection to better capture the dynamic evolution of land surfaces has become an important research direction. However,from a data perspective,high-resolution,high-quality multitemporal remote sensing change detection datasets that cover diverse land surface change types remain scarce. Most widely used change detection datasets remain limited to bitemporal imagery with corresponding annotations,primarily describing changes between two discrete time points. These datasets are often constrained in terms of the number of temporal phases,spatial coverage,image scale,and temporal span. As a result,they are insufficient for modeling and analyzing long-term,stage-wise land surface evolution processes,particularly in complex application scenarios such as urban expansion and ecological transformation.To address these limitations,this study constructs a high-resolution,multiregional,and multitemporal remote sensing change detection dataset,termed HR-MTCD (high-resolution multitemporal change detection),with the aim of providing fundamental data support for dynamic land surface evolution modeling.

Method

The dataset covers five representative regions in China,including the Yangtze River Delta,the Pearl River Delta,the Beijing-Tianjin-Hebei region,the Chengdu-Chongqing region,and Northwest China. It integrates multiple types of land surface changes related to urban development and ecological evolution. The dataset spans a five-year period,with changes annotated at one-year intervals,and consists of 1 601 change groups and 8 005 remote sensing images with a spatial resolution of approximately 0.5 meters. The change categories primarily focus on prominent land surface changes,such as building construction and demolition,and large-scale vegetation changes while covering typical scenarios related to urban growth and ecological dynamics. This design ensures the dataset’s practical applicability and relevance,providing robust support for research on diverse land surface changes and for the development of multitemporal change detection algorithms.

Result

Systematic experiments conducted using several mainstream change detection models reveal performance differences among models and validate the usability and the inherent challenges of the proposed high-resolution multitemporal dataset in real-world change detection tasks. Within a unified experimental framework,we further design progressive cross-temporal extension experiments. By comparing detection performance as training data from different temporal spans are incrementally incorporated,we evaluate the influence of multitemporal data on a model’s ability to recognize long-term,nonlinear,or gradual land surface changes. Experimental results demonstrate that the temporal dimension information contained in multitemporal remote sensing imagery plays a fundamental role in change detection tasks,offering new perspectives for models to understand dynamic land-cover evolution.

Conclusion

Overall,the construction of the HR-MTCD dataset provides an important data foundation for advancing remote sensing change detection from discrete bitemporal change identification toward comprehensive modeling of multitemporal land surface evolution processes.In future work,the dataset will be continuously expanded to cover a broader range of geographical regions and longer temporal spans to better capture diverse land surface dynamics under different environmental and socioeconomic conditions. In addition,we plan to incorporate multisource remote sensing modalities progressively,including optical imagery,synthetic aperture radar,and LiDAR data,thereby enabling complementary representations of land surface structure,texture,and physical properties. Beyond geometric and radiometric changes,semantic-level change information will also be introduced to describe higher-level land-cover transitions and functional transformations. The dataset is publicly available at https://doi.org/10.57760/sciencedb.j00240.00110.

remote sensing change detection(RSCD)  /  multi-temporal high-resolution dataset  /  urban expansion monitoring  /  ecological evolution analysis  /  temporal land surface dynamics
周建泉, 陈静波, 邓毓弸, 孟瑜, 陈建胜, 隋晨红. 高分辨率多时相遥感变化检测数据集构建与验证. 中国图象图形学报, 2026 , 31 (10) : 3572 -3589 . DOI: 10.11834/jig.250563
Jianquan Zhou, Jingbo Chen, Yupeng Deng, Yu Meng, Jiansheng Chen, Chenhong Sui. Construction and validation of a high-resolution multitemporal remote sensing change detection dataset[J]. Journal of Image and Graphics, 2026 , 31 (10) : 3572 -3589 . DOI: 10.11834/jig.250563
地表变化信息的获取是认识自然环境演化与人类活动影响的重要途径(Zhang等,2024;Lyu等,2024)。地表变化反映了自然过程与人类活动共同驱动的景观格局演变,这些变化不仅受自然因素影响,也与社会经济发展密切相关(Zhu等,2022)。对这些变化进行及时、准确的监测与识别,不仅有助于深入理解区域生态演替与城市扩张规律,也能为国土空间规划、生态环境保护和社会治理提供科学支撑。遥感变化检测(remote sensing change detection,RSCD)是遥感与地理信息科学中的重要研究方向,近年来受到越来越多的关注。遥感变化检测的核心任务就是通过双时相或多时相的遥感影像,识别同一地理区域内的地物元素在不同时间点发生的显著变化(王艳恒 等,2020),为城市规划(Lyu等,2018)、土地管理(Das和Angadi,2022)、生态环境监测(Gao等,2019)及灾害评估(Saha等,2018)等提供可靠的数据支撑。
当前研究主要聚焦于双时相变化检测,即基于前后两个时间点的遥感影像进行变化识别。这一研究范式在过去取得了显著进展。以卷积神经网络(convolutional neural network,CNN)为核心的变化检测方法,通过特征差分、拼接或注意力融合实现变化区域提取,如FC-EF(fully convolutional early fusion)(Caye Daudt等,2018)、DSIFN(deeply supervised image fusion network)(Zhang等,2020)、SNUNet(the combination of siamese network and nested U-Net)(Fang等,2022)等网络模型在多种公开数据集上表现优异。随后,Transformer结构被引入变化检测任务,以全局自注意力机制增强长距离依赖建模能力,典型方法如ChangeFormer(Bandara和Patel,2022)、BIT(bitemporal image transformer)(Chen等,2022)和Changer(Fang等,2023)等,在复杂场景下显著提升了空间一致性与边界识别精度。近年来,随着基础模型(foundation model)的兴起,研究者开始探索将大规模预训练视觉模型应用于变化检测任务。这类方法如TTP(time travelling pixels)(Chen等,2024)和BAN(bi-temporal adapter network)(Li等,2024)通过引入具有通用视觉表征能力的预训练骨干,有效缓解了传统变化检测在标注样本有限、域间差异显著等场景下的性能瓶颈,充分挖掘了基础模型的视觉知识与迁移潜力,为变化检测任务提供了新的范式与方向。
尽管双时相方法在精度和效率上不断提升,但其时间维度建模能力仍然有限。现实世界中的地表变化往往具有连续性、阶段性与多尺度时序特征(van Etten和Hogan,2021),例如城市建设的逐步扩张(Zhao等,2024)、植被退化与恢复的季节性波动(Zhu等,2025)以及灾害后地表恢复的非线性过程等。仅依赖前后两个时相影像,难以准确刻画这些长期演化与复杂动态变化模式,同时也难以识别缓变或周期性变化中的隐性趋势(Sexton等,2013)。此外,由于仅包含前后两个时相影像,双时相方法在面对光照差异、观测噪声等问题(Zhao等,2024)时,更容易出现伪变化与误分类现象。因此,探索多时相变化检测(multi-temporal change detection,MTCD),通过引入更丰富的时间序列信息以刻画地表演化过程的动态变化,已成为当前遥感智能解译领域的重要发展方向。
然而,从数据基础角度看,高分辨率、高质量且涵盖多类型地表变化的多时相遥感变化检测数据集仍然匮乏。目前主流的变化检测数据集,如LEVIR-CD(LEVIR change detection)(Chen和Shi,2020)、WHU-CD(Wuhan University change detection)(Ji等,2019)、SYSU-CD(Sun Yat-sen University change detection)(Shi等,2022)、SECOND(semantic change detection dataset)(Yang等,2020)和DSIFN-CD(deeply supervised image fusion network change detection)(Zhang等,2020)等,大多仅包含双时相影像及对应标签,主要刻画两个离散时间点之间的变化关系,在时相数量、覆盖区域、图像规模和时间跨度等方面普遍受限。这类数据集难以支撑对跨多年、分阶段地表变化过程的建模与分析,在城市扩张与生态演化等复杂应用场景中存在明显不足。近年来,尽管出现了一些多时相变化检测数据集如TSCD(time series change detection)(Zhao等,2024)和ChangeNet(Ji等,2024)等,但仍存在区域单一、变化类型局限或规模过大难以训练等问题。例如,TSCD数据集仅涵盖成都区域且仅关注建筑物变化,难以反映多类型地物的综合演化特征;而ChangeNet数据集在空间覆盖范围和样本规模方面具有显著优势,但其较大的数据规模以及标注与获取过程中的实际复杂性,在一定程度上增加了数据使用与实验复现的成本。这使得多时相方法的训练与验证往往依赖于合成或自建数据(Zhao等,2024),从而限制了算法在真实复杂场景中的推广与评估。因此,变化检测领域亟需一个覆盖多区域、多类型地物变化、具备高空间分辨率与时序连续性的多时相变化检测数据集,既能支撑地表动态建模与趋势分析,又能兼顾数据规模的可复现性与训练可行性。
针对上述问题,本文构建了一个覆盖多区域、多时相、高分辨率的遥感变化检测数据集HR-MTCD,旨在为多时序地表动态建模提供基础数据支撑。该数据集覆盖中国五大典型区域——长三角、珠三角、京津冀、成渝及西北地区,融合城市扩张与生态环境演变等多类型地表变化。数据时间跨度为5年(每隔一年标注一次变化),共包含1 601组、8 005幅分辨率约0.5 m的遥感影像。变化类别聚焦于建筑物新增或拆除、大面积植被变化等显著地表变化,兼顾城市发展与生态变化等典型场景,确保数据的实际应用价值。
为验证所构建的高分辨率多时相遥感变化检测数据集在场景复杂性、多类型变化等方面的挑战性与代表性,本文选取了多种具有代表性的主流变化检测模型进行系统评估,涵盖基于卷积神经网络、Transformer和基础模型的变化检测方法。在统一的实验框架下,进一步设计多时相输入方案,以验证时间维度信息对变化检测性能与模型泛化能力提升的作用和潜力。
本文的主要贡献如下:1)构建并公开一个覆盖多区域、多时相且具备高空间分辨率的遥感变化检测数据集,明确变化定义与标注规范,重点涵盖建筑物新增与拆除、大面积植被变化等典型地表变化类型,可为城市扩张监测、生态演变分析等多类型地表变化研究提供可靠的数据支撑与验证基准;2)设计多模型对比与多时相验证实验,系统评估主流变化检测模型在多时序场景下的性能差异,验证多时相信息在提升变化检测精度与结果稳定性方面的有效性。
随着遥感观测技术的持续进步与高分辨率影像获取能力的提升,遥感影像变化检测在城市扩张监测、生态环境评估以及灾害应急响应等领域发挥着越来越重要的作用。为推动算法研究与模型评估,国内外学者已构建并公开了多种变化检测数据集,其中具有代表性的包括WHU-CD、LEVIR-CD、DSIFN-CD、SYSU-CD、S2Looking(Shen等,2021)、CLCD(cropland change detection)(Liu等,2022)、SECOND和BANDON(building change detection with off-nadir images)(Pang等,2023)等。
这些数据集大多采用亚米级高分辨率遥感影像,覆盖不同区域、时间段和地物类型,在支持深度学习方法的训练与验证方面发挥了重要作用。WHU-CD数据集是武汉大学建筑物数据集的一个子集,选取新西兰克赖斯特彻奇地区2012年与2016年的两期航空影像,分辨率为0.3 m,主要用于建筑物新增或拆除变化检。LEVIR-CD数据集基于大幅面航空影像切块构建,空间分辨率0.5 m,主要关注建筑物变化任务。SYSU-CD数据集则面向城市与沿海地区场景,重点反映高层建筑与基础设施发展的地表动态变化,场景多样性更强。
从数据组织形式来看,上述多数数据集均采用双时相设计,即仅包含两个离散时间点的遥感影像及其对应变化标注。这类数据集在建筑物变化识别等任务中表现出良好的适用性,但其时序维度有限,难以完整表达地表覆盖随时间演化的连续过程。近年来,研究者开始尝试构建多时相变化检测数据集,如TSCD(Zhao等,2024)和ChangeNet(Ji等,2024)。其中,TSCD数据集聚焦单一区域的建筑物变化,适用于局部城市建成区的演化分析;ChangeNet数据集在空间覆盖范围与样本规模方面具有优势,但其数据体量与标注复杂度对模型训练资源和实验复现提出了更高要求。表1对当前代表性的高分辨率光学遥感影像变化检测数据集进行了简要对比与总结。
在20世纪70—80年代,学者提出变化检测的概念并逐步关注到利用遥感影像提取变化信息(Singh,1989;Weismiller等,1977;Bruzzone和Prieto,2000),相关研究经历了从传统方法到深度学习方法的持续演进(王仁芳 等,2025)。早期研究主要依赖光谱差分、主成分分析(Deng等,2008)、变化向量分析(Du等,2020)等传统统计方法,但在复杂背景和非线性变化场景下鲁棒性有限。随着深度学习在计算机视觉领域的突破,研究者开始将其强大的表征与建模能力引入遥感变化检测,大幅提升了检测精度、语义一致性和空间细节恢复能力。
卷积神经网络(CNN)凭借优秀的局部特征建模能力,成为最早广泛应用于遥感变化检测的深度架构之一。Caye Daudt等人(2018)开创性地将全卷积网络(fully convolutional network,FCN)引入变化检测领域,提出了3种全卷积结构。Early fusion架构直接对双时相图像进行通道拼接后输入网络,结构类似U-Net;Siamese FCN架构采用孪生(siamese)网络分别提取两个时相的特征,再进行差异建模,同时系统比较了early fusion、late fusion等融合策略对变化检测性能的影响。随后,Zhang等人(2020)提出的DSIFN通过双流特征提取与深度监督机制,并辅以多层次特征融合,有效提升了变化区域的边界完整性与检测精度;Fang等人(2022)的SNUNet则结合孪生网络与嵌套式U-Net结构,借助密集连接强化了跨层特征交互与小尺度变化识别的能力;Han等人(2023)通过结合渐进式前景平衡采样与层次化注意力网络HANet(hierarchical attention network)等关键设计,有效缓解了变化检测中的类别不平衡问题,提升了对少数类变化的检测敏感性。总体而言,CNN架构在局部结构表征方面表现突出,但受限于卷积算子的感受野,其全局上下文建模能力有限,难以有效捕捉大尺度时空依赖。
Transformer架构因其自注意力机制具备长程依赖建模能力,逐渐成为变化检测的重要研究方向。Chen等人(2022)提出的BIT模型通过将双时相图像压缩为语义标记并由Transformer编码器和解码器架构进行上下文建模,实现了高效的全局时空信息交互。随后,Bandara和Patel(2022)提出纯Transformer架构的孪生网络ChangeFormer,它的核心设计是将分层结构的Transformer编码器与多层感知机(multi-layer perceptron,MLP)解码器结合,在双分支结构中分别处理两个时相影像,从而建模其间的语义变化;Zhang等人(2022)提出的SwinSUNet(swin transformer-based siamese U-shaped network)引入层次化Swin Transformer模块构建完整的编码—融合—解码流程,进一步细化空间与时间特征交互与融合;Li等人(2022)提出了TransUNetCD(Transformer-UNet hybrid network for change detection)混合架构,该模型通过结合Transformer与U-Net的优势建模全局上下文与局部特征,并引入一个专用的差分增强模块,以选择性聚合信息,从而强化了对变化特征的表征能力。总体来看,Transformer在全局上下文建模与特征交互方面具有优势,但计算成本较高,且纯Transformer架构在局部结构与边缘细节建模方面存在一定不足。
随着基础模型在计算机视觉中的快速发展,其强大的通用视觉表征能力为遥感变化检测提供了新的方法思路。典型方法包括BAN(Li等,2024)和TTP(Chen等,2024)。BAN基于冻结的基础模型如CLIP(contrastive language image pre-training),结合双时相适配分支(Bi-TAB)以及连接两者的桥接模块,将通用特征有效注入任务特定模块,从而实现多源数据的高效适配和变化特征提取。TTP则在基础模型主干中引入低秩微调参数,并设计时序特征激活门,使不同时相信息能够在像素语义空间中充分交互,同时通过多层级预测头解码高阶语义变化特征。总体来看,基于基础模型的方法在继承全局感知和丰富语义表征能力的同时,通过适配机制实现任务特定特征提取和多时相交互,有效提升了模型在复杂场景下的变化检测精度与稳健性,为遥感变化检测从局部差异识别向全局语义理解提供了新方向。
尽管现有主流方法在双时相变化检测任务中取得了显著进展,但现实地表变化往往具有连续性、阶段性与非线性特征,仅依赖前后两期影像难以刻画其完整演化过程。为此,学界开始探索多时相变化检测,通过引入时间序列遥感数据实现地表动态建模与长期趋势分析。代表性工作之一是SpaceNet 7挑战赛(Van Etten和Hogan,2021)提出的MUDS(multi-temporal urban development dataset),该数据集整合了2017—2020年间101个城市区域的中分辨率Planet影像,首次支持建筑物在时序维度上的持续检测与生命周期建模。该研究提出了结合时序卷积与掩膜预测的基线模型,实现了城市扩张过程的动态追踪,为多时相建筑变化研究奠定了基础。然而,MUDS数据集受限于较低空间分辨率(4 m)、单一地物类型与有限时间跨度,难以支持高精度地表要素变化与生态动态分析。
此外,Zhao等人(2024)提出的COUD(continual urbanization detector)框架利用高分辨率TSCD数据集实现了四时相建筑物变化检测,设计了时序一致性约束与增量式学习机制,在连续场景中有效提升了模型对城市化动态的识别能力。尽管此类研究初步验证了多时相建模的潜力,但仍局限于单区域、单要素任务,TSCD 数据集仅涵盖成都区域且仅关注建筑物变化,难以反映多类型地物的综合演化特征。
多时相变化检测的研究尚处于起步阶段,受限于缺乏高质量、多区域和标准化的时序数据集,模型验证往往局限于局部场景。针对上述问题,本文构建了一个覆盖典型城市与生态区域、具备高分辨率与时间连续性的多时相变化检测数据集,为未来多时相建模与动态地表演化研究提供数据支撑。
本文构建并发布一个覆盖中国典型城市群与生态区的多时相数据集HR-MTCD,聚焦城市扩张与生态变化的连续地表变化过程。本数据集所使用的影像均来源于Google Earth历史高分辨率光学影像,数据仅限于学术研究用途,其使用遵循Google Earth的相关服务条款与使用规范(https://www.google.com/per-missions/geoguidelines/)。数据集以亚米级空间分辨率(约0.5 m)的高分辨率光学影像为主体,时间上横跨5年,按照逐年标注、连续对齐的原则组织样本。数据集包含1 601组影像,共8 005幅影像,图像尺寸为512 × 512像素,空间上覆盖多个典型区域。标注采用全要素二元变化策略,该数据集既支持双时相变化检测,也支持多时相建模与趋势分析,为遥感变化检测从离散双时相变化识别向多时相地表变化过程刻画提供重要数据基础。
本研究在区域选择上考虑了自然地理特征、城市化水平及变化多样性,选取了长三角地区(约31.0°~32.5°N,119.0°~121.5°E)、珠三角地区(约22.0°~23.5°N,112.5°~114.5°E)、京津冀地区(约38.5°~41.0°N,115.5°~117.5°E)、成渝地区(约28.5°~31.0°N,103.0°~106.5°E)和西北干旱区(以张掖为代表,约38.5°~39.5°N,100.0°~101.5°E) 5个典型区域。首先,长三角地区作为中国最典型的超大城市群,具有高度集约化和碎片化的空间格局,城市建成区密度高、功能区混合度强。其次,珠三角地区作为快速工业化和城市化的滨海区域,呈现出“港口—产业—城市”紧密耦合的空间形态,土地利用变化以大规模填海造地与产业园区集聚式扩张最为显著。再次,京津冀地区在多中心城市体系和密集交通基础设施建设的驱动下,表现为城市空间的多向外溢与扩展。与此同时,成渝地区典型地呈现山地城市空间格局,城市开发受限于地形条件而沿河谷及坡地呈带状或组团式拓展,新区开发与传统城区更新叠加,形成复杂的时空演化特征。最后,西北干旱区(以张掖为代表)位于绿洲—荒漠过渡带,具有高度的生态脆弱性,土地利用变化不仅受城市化进程影响,更与农业灌溉扩展、牧业活动波动以及生态修复措施密切相关。整体而言,这五大区域在城市化动力、自然地理约束及生态过程方面均存在显著差异,能够充分反映中国多样化地表覆盖变化模式,为构建具有普适性与挑战性的数据集提供了坚实基础。
为兼顾时间连续性与标注效率,本数据集跨越5年时间跨度,每隔一年选取一个时相,共形成5个时相影像。多时相影像在获取时尽量保持季节一致或相近,减少因季节性差异带来的光谱扰动,从而更准确地反映地物真实变化。标注遵循全要素变化原则,重点刻画人造地物的新增、拆除及显著的生态变化(如植被退化与恢复、裸地扩展与回填),排除季节性和短暂性变化(如农作周期、临时施工等),以确保变化表征的真实性与时序稳定性。该策略使数据集在聚焦城市扩张的同时,兼顾生态演变过程,增强了数据集的适用范围与研究价值。
为在保证标注精度与一致性的前提下有效控制人力成本与时间开销,本文采用一种增量式(Ji等,2024)、模型辅助的多时相遥感变化标注策略。设一个多时相影像序列
I
为
I1,I2,…,IN
,其中
IN
表示第
N
时相影像。每幅影像通常包含复杂的地物类型与丰富的空间上下文信息,若一次性展示全部
N
幅影像,不仅会造成视觉负荷过高,也容易导致标注者对不同时间点变化关系的判断偏差。为此,本文在标注界面上采用逐对展示的方式,即每次仅展示相邻两期影像,使标注者能够专注于两时相之间的变化差异,从而显著提升标注的准确性与一致性。
在理想情况下,若对
N
时相影像进行全组合标注,需人工完成
N×(N-1)/2
次图像配对与变化标注,随着时相数增加,标注量呈平方级增长,既耗时又难以维持标注质量。为降低复杂度并兼顾时间维度信息,本文基于地表变化的时序渐进性假设,仅对时间上相邻的影像对进行标注,即只在
I1,I2,I2,I3,…,IN-1,IN
之间人工确定变化区域。该策略基于现实观测:多数地表变化(如城市建筑物新增、农田转化或植被退化)具有累积性与连续性,相邻时相之间的变化最能反映真实演化过程。通过这种增量式标注方式,可以在保持变化检测逻辑完整的同时,将人工标注次数由平方级降为线性级,大幅提升标注效率。
此外,为进一步提升标注质量与一致性,本文引入了模型辅助标注。首先利用已有双时相变化检测模型在初步选取的影像对上进行预训练,生成参考变化掩膜,并将其叠加至标注界面供人工参考(图1为某一区域两个时相影像的变化情况,左侧紫色阴影区域为模型预测的变化区域,右侧红色阴影区域为最终人工修订后的标注结果)。标注者可在模型初判结果的基础上对误检与漏检区域进行精细修正,从而显著降低人工标注的工作负担,并有效减少因主观因素导致的标注差异。为确保标注结果的准确性与可靠性,本研究采用“模型辅助—人工修订—交叉复核”的三阶段标注机制,如图2所示。最终,所有标注成果均须经过多轮交叉验证与一致性审查,从而确保标注结果在空间范围界定与语义定义上达到高度的统一性与科学性。
这种标注流程兼具高效率、时序一致性与语义严谨性,为构建大规模、多时相、高分辨率遥感变化检测数据集提供了一种可推广的解决方案。
在数据组织上,数据集以“组”为基本单位,每组包含5个时相的影像切片,切片尺寸统一为512 × 512像素,便于直接用于深度学习模型训练。大部分样本仅包含少量变化像素(变化比例 < 15%),而少数样本存在显著突变场景如新区开发、旧城改造、耕地转建设用地等,构成模型训练中典型的类别不平衡挑战。同时,现有多数公开变化检测数据集的不同时间影像通常在固定参数条件下采集,外观一致且几乎不存在几何扭曲;而在真实应用中,跨时序影像往往来源于不同的拍摄角度和成像条件,尤其在高层建筑密集或地形复杂区域,视角差异会引起显著的结构扭曲与位移。此类现象在本数据集中被真实保留,使模型在区分真实变化与几何差异时面临更高挑战,从而提升了数据集的真实性与研究价值。
本文对各区域样本数量等进行了统计分析(见表2),并选取具有代表性的样本组展示典型影像与变化类型(如图3所示)。这些样例涵盖了多类型的地表演化情形,全面反映了人类活动驱动下土地利用的动态变化过程。样例中既包含城市更新与再开发过程,如原有棚户区被清除后转变为停车场(如样例1),展现了城市空间结构的重塑与功能替代;也体现了农业用地向建设用地转化的趋势,如在耕地上建设温室大棚(如样例2),以及水田、草地被逐步开发为建设用地(如样例3和样例4),反映了土地集约化利用与城乡扩张的进程。同时,部分样例揭示了建设用地内部的持续演化与垂直扩展特征,例如建筑物群体的逐步建设(如样例5)、高层建筑群的集中发展(部分伴随拍摄视角差异导致的结构变形)(如样例6)。此外,还可观察到生态用地转化与恢复并存的现象,一方面草地、林地被开发为建设用地(如样例7和样例8),体现出城市扩张对自然生态空间的侵占;另一方面,部分建设用地及草地被恢复为耕地(如样例9),反映了土地退化治理与再利用的趋势。部分区域的变化亦与交通枢纽建设密切相关,如机场附近干线沿线的新建建筑群(如样例10),呈现出典型的基础设施带动的空间集聚效应。这些示例展示了不同地理环境下的地物变化特征及其在多时相序列中的演化过程。
综上所述,本文构建的多时相高分辨率全要素变化检测数据集,充分体现了多源、多尺度与多类型融合的特征。该数据集覆盖典型城市群与干旱地区,兼具空间多样性与区域代表性,为跨区域泛化与迁移学习研究提供了坚实支撑。其精细的全要素标注不仅适用于城市扩张、基础设施建设等人类活动驱动的变化分析,也为生态退化与恢复等自然过程监测提供了数据基础。与此同时,数据结构设计兼容双时相与多时相建模任务,可服务于变化检测模型的性能评估、时序演化建模与长期趋势预测,为前沿方法研究与模型泛化验证提供了统一且高质量的数据支撑。
为验证所构建的高分辨率多时相遥感变化检测数据集在场景复杂性、多类型变化等方面的挑战性与代表性,系统评估不同变化检测模型在多时相高分辨率遥感场景下的表现,并验证多时相数据在变化检测任务中的实际价值,本研究的实验分为两个层次:基线模型对比实验与多时相有效性验证实验。
针对基线模型对比实验,本文选取当前主流的变化检测模型作为基线方法,涵盖基于CNN、Transformer和基础模型的变化检测方法。为适配模型方法结构,构建相邻时相变化组(T1&T2、T2&T3、T3&T4、T4&T5)同时输入模型并利用相应的变化标签进行监督训练与测试。每一对影像均对应一幅二元变化标注图,标注区分“变化”与“非变化”两类像素。所有影像在数据整理过程中进行了统一的空间配准、裁剪与尺寸规范化处理,并尽量保证不同时间影像在空间参考和观测条件上的一致性,以减少非变化因素对变化检测结果的影响。实验将成都区域作为测试,用于直观反映模型在陌生环境下的迁移与适应能力,即模型面对不同空间分布的性能表现。此外,为验证模型在不同地貌条件与城市群环境下的泛化能力,本文额外构建了一个跨区域测试集,包含180组多时相样本(共900幅影像),覆盖文中涉及的长三角、珠三角、京津冀、成渝及西北干旱区等多个典型区域。该测试集目的在于评估模型在多区域、多地貌条件下的泛化表现。通过在相同数据、相同训练策略下的横向对比,能够直观反映各类模型在不同地理区域、不同变化类型下的表现差异,从而分析模型对复杂地表变化的适应性,同时验证所构建的高分辨率多时相遥感变化检测数据集在场景复杂性、多类型变化等方面的挑战性。
针对多时相信息有效性的验证,本文在相邻时相数据的基础上,设计了递进式跨时相扩展实验。在不增加额外标注即总体标签信息量不变的前提下,构建了跨时相变化组,通过逻辑叠加(logical OR)中间年份标签生成长跨度变化样本,包括跨两年(T1&T3、T2&T4、T3&T5)、跨3年(T1&T4、T2&T5)及跨4年(T1&T5)等多级跨度组合。加入不同跨度的跨时相样本与原有相邻样本共同参与训练,并在与第1阶段实验相同的成都区域测试集(T1&T2、T2&T3、T3&T4、T4&T5)上进行验证。具体而言,共3轮递进实验,实验1以相邻时相变化组为基础,加入跨两年的变化样本(T1&T3、T2&T4、T3&T5)共同参与训练;实验2在实验1的训练集基础上进一步加入跨3年样本(T1&T4、T2&T5);实验3在实验2的训练集基础上继续加入跨4年样本(T1&T5)。实验设计如图4所示。本文从数据组织与监督形式的角度出发,在保持模型输入形式不变的前提下,引入多样化的时间跨度样本,对时间信息的潜在作用进行隐式分析,突出多时相数据本身对变化检测任务的影响。通过比较加入不同跨时相数据训练的检测性能变化,评估多时相数据对模型识别长期、非线性或缓变地表变化的影响,从而分析其在变化检测任务中的潜在价值。
总体而言,本实验设计从模型结构与时间维度两条主线展开:一方面,通过对比不同架构类型(CNN、Transformer与基础模型)的性能表现,系统分析各类模型在高分辨率、多类型地表变化场景下的适应性与泛化能力;另一方面,通过引入不同跨度的跨时相样本,探讨时间维度信息在变化检测中的作用机制。两类实验相互补充,既反映了不同模型在复杂遥感场景下的性能差异,也探讨了多时相数据在提升变化检测精度与鲁棒性方面的潜在价值,为后续多时序遥感变化建模与动态地表演化分析提供了系统的实验依据。
为确保对比实验的公平性,所有模型采用统一的数据预处理方式、训练策略与评估流程。主要设置如下:
1)数据预处理。首先,对原始双时相影像进行尺寸裁剪,裁剪大小统一为512 × 512像素;随后执行多种随机增强操作,包括随机旋转、缩放等,以提升模型对几何与光谱变化的鲁棒性。增强过程中保持两时相影像的空间对应关系不变,确保语义一致性。
2)优化策略。优化器采用AdamW,初始学习率设为5 × 10⁻⁴,结合线性预热(linear warm-up,Linear)与多项式衰减(polynomial learning rate decay,PolyLR)的学习率调度策略进行优化。
3)损失函数。解码头采用交叉熵损失(cross entropy loss,CrossEntropyLoss)进行监督训练,训练过程中未对不同类别设置额外权重。
4)训练参数。模型基于迭代制训练(iteration-based training loop,IterBased- TrainLoop)进行,总迭代次数设为50 000,总批次大小为8。
5)评价指标。为全面评估模型性能,采用精确率(precision)、召回率(recall)、F1分数(F1-score)与交并比(intersection over union,IoU)等常用变化检测指标。其中,IoU衡量变化区域的空间重叠程度,F1-score综合反映模型的检出能力与稳定性。
实验在配备NVIDIA GeForce RTX 3090 GPU(24 GB 显存)的多卡服务器上进行。对于显存开销较大的模型(如TTP),通过增加并行GPU数量以满足显存约束,其余模型采用2张GPU完成训练。所有模型均采用一致的有效批次规模(effective batch size),不同GPU数量仅用于满足显存需求。
所有实验均在相同硬件与软件环境下执行,以保证结果的可比性。
表3和图5分别展示了不同类型变化检测模型在所构建数据集上的性能与两组样例的可视化表现。从整体上看,各类模型在精确率(precision)与召回率(recall)之间存在显著差异,反映出不同结构在应对复杂地表变化时的偏向性。总体而言,Transformer与混合架构模型在全局表征与变化模式识别上具有明显优势,而传统CNN模型在边缘细节与局部纹理保持方面表现较好。
1)基于卷积神经网络的变化检测方法。在纯CNN架构中,TinyCD_v2(L)取得了55.8%的F1分数和38.69%的IoU,但模型的高精确率(77.99%)与低召回率(43.44%)表明该模型在“变化”类样本的判定上较为保守,更倾向于稳定识别显著变化区域,而对弱变化或渐变类样本的敏感性不足。DSIFN在CNN组中表现最佳,F1分数为64.85%,IoU为47.99%,其基于双分支特征交互与差异增强的设计能够更好地对齐多时相特征,并在像素级差异提取上展现出更强的鲁棒性。
2)基于Transformer的变化检测方法。Transformer架构整体优于传统CNN,尤其在召回率上具有明显优势,体现了其在建模长距离依赖和捕捉全局语义变化方面的潜力。其中,ChangeFormer在本阶段实验中表现最优,F1分数达到65.21%,IoU为48.38%,精确率和召回率分别为79.89%和55.09%,在全体模型中均居前列。Changer与ChangeStar的性能次之(F1分别为57.95%和52.43%),其中Changer在召回率上较高(46.12%),表明其在识别变化区域方面更敏感。相比之下,ChangeStar虽然结构轻量,但在复杂变化场景下的整体性能相对有限。
3)CNN-Transformer混合架构分析。BIT模型作为典型的混合结构,将CNN的局部特征提取与Transformer的全局关系建模相结合,其在 ResNet50骨干下的F1分数为58.05%,IoU为40.89%,较ResNet18提升约5%,验证了更深CNN骨干网络(backbone)的正向作用。然而,相较于纯Transformer模型,BIT的整体性能仍略有差距,这可能与其在引入Transformer时采用的词元(token)压缩策略及模块规模相对受限有关,在一定程度上影响了对跨时相细粒度变化模式的刻画能力。
4)基于基础模型的变化检测方法。基础模型展现出明显的性能优势。TTP模型在所有方法中表现最优,F1分数达到73.52%,IoU达到58.12%,显著超越传统与混合架构。其高召回率(71.94%)说明模型对多尺度、弱变化目标具有较高敏感度,而精确率亦保持在75.16%,表明整体预测稳定。BAN性能略低,但在同类方法中仍处于上游,说明利用预训练视觉模型(如CLIP)进行跨域知识迁移能够有效提升遥感变化检测的泛化能力。这类模型能够更充分地捕捉地物的语义一致性与时间演化特征,在地表变化较复杂的区域(如城市边缘或多类地物交错区域)中表现尤其优越。
从总体趋势来看,模型性能随结构复杂度与语义建模能力的增强而稳步提升。CNN到Transformer再到基础模型方法的性能递进清晰,F1分数分别约为45%~65%、50%~66%、63%~74%。Transformer结构在平衡精确率与召回率方面表现最佳,而基础模型进一步突破了这一平衡瓶颈,在召回率保持高水平的同时维持较高精确率。IoU指标的提升亦表明高层语义建模能够显著增强模型对变化区域空间边界的一致性判断。
为了进一步验证模型在不同地理区域和多地貌条件下的泛化能力,本文在额外构建的跨区域独立测试集上进行评估。表4汇总了各类模型在跨区域测试集上的主要指标。总体趋势与成都测试集类似:基础模型方法在F1和IoU指标上依旧表现最佳,Transformer模型次之,而传统CNN模型在整体性能上略逊一筹。具体来看,TTP模型在跨区域测试集上的F1达到74.8%,IoU为59.74%,精确率和召回率分别为75.24%和74.36%,说明其对多区域、多类型变化具有较强适应性。ChangeFormer模型最高 F1为65.61%,IoU为48.83%,也表现出稳健的迁移能力。传统CNN模型如DSIFN在跨区域测试集的F1略下降(63.92%),反映出对细微变化及不同地貌环境的敏感性有所不足。
总体而言,TTP模型表现最佳,ChangeFormer模型次之,DSIFN作为传统CNN模型的代表表现最优。这些结果不仅揭示了不同模型在变化检测任务中的性能差异,也反映出本文所构建的高分辨率多时相遥感变化检测数据集在场景复杂性、变化类型多样性与时序跨度方面的挑战性。多数模型在召回率上仍存在明显不足,说明数据集中包含的大量细微、缓变及非线性变化对现有模型仍具较高识别难度,这从侧面验证了该数据集的研究价值与代表性。
基于上述对比,本文进一步选取部分具有代表性的变化检测方法开展递进式跨时相扩展实验。如前所述,在不增加额外人工标注,即总体标签信息量保持不变的前提下,通过对中间年份标签进行逻辑叠加(logical OR),构建了跨2年、跨3年及跨4年的多级跨度变化样本,形成统一的长跨度变化组。随后,将这些跨时相样本与原有相邻年份样本共同用于训练,并在与第1阶段完全一致的成都区域测试集上进行验证,以确保实验可比性。
实验结果如表5所示。从整体表现来看,在相同实验设置下,3种模型在引入跨时相训练样本后均出现了不同程度的性能提升,说明了时间维度信息在变化检测中具有重要价值。
在3个模型中,ChangeFormer表现最为优异,F1分数从仅使用相邻时相数据的62.86%(1年跨度)逐步提升至67.21%(3年跨度),在引入跨3年样本后达到峰值,随后在跨4年阶段略有下降(65.74%)。该趋势说明引入过长跨度时相样本可能因影像时序差异过大标签叠加误差而引入噪声或伪变化,导致性能轻微回落。TinyCD_v2的性能呈现相对稳定的递增趋势,F1分数从55.8%提升至62.76%,IoU从38.69%提升至45.73%,说明该轻量级模型在跨时相扩展后能够逐步捕获到更多稳定的变化特征,尽管其总体精度略低于ChangeFormer,但表现出较好的跨时相适应性。相比之下,BIT模型在不同跨度间的波动较小(F1分数约52.93%~55.89%),但仍表明引入跨时相训练样本后模型性能提升。从精确率与召回率的变化可以看出,3种模型在引入跨时相样本后,精确率保持在较高水平,而召回率均显著提升。特别是ChangeFormer 的召回率从52.16%提升至60.21%,表明模型在跨时相训练后对真实变化区域的覆盖能力增强,有效缓解了仅依赖相邻时相训练时的“变化漏检”问题。IoU指标的提升进一步验证了跨时相样本的有效性。具体地,在Change Former中,IoU在引入跨3年样本时达到最高值(50.61%),在TingCD_v2中,IoU在引入跨4年样本时达到最高值(45.73%)。这说明模型在多时相样本的联合训练下,能够在空间上形成更稳定的变化区域预测,增强了对长期累积变化特征的整合能力。在可视化结果中(如图6所示),同样说明了跨时相样本的加入对于模型在真实变化区域的覆盖能力增强,有效缓解了仅依赖相邻时相训练时的变化漏检和错检问题。
跨时相变化样本的构建基于对中间年份变化标注的逻辑叠加,该过程在一定程度上可能引入标签噪声或导致变化边界模糊,尤其在时间跨度较大的情况下更为明显。然而,实验结果表明,即便在存在上述潜在噪声的前提下,引入跨时相训练样本仍能够在多个模型上带来稳定的性能提升,特别是在召回率和IoU指标上表现突出。这一结果从侧面说明,多时相遥感影像所包含的时间维度信息带来的有效变化线索在一定程度上能够抵消标签噪声带来的负面影响。与此同时,实验中观察到当时间跨度过大时部分模型性能出现轻微回落,也反映出跨时相样本构建在时间跨度选择上需要权衡噪声引入与性能增益之间的关系。
本文构建并公开了一个面向中国典型区域的多时相高分辨率遥感变化检测数据集,采用全要素标注与多区域设计,旨在为复杂真实场景下的变化检测研究提供可靠的数据基础。通过在多种主流变化检测模型上的系统实验,揭示了不同模型在变化检测任务中的性能差异,验证了本文所构建的高分辨率多时相遥感变化检测数据集在实际变化检测任务中的可用性以及所具备的客观挑战性。在统一的实验框架下,进一步设计了递进式跨时相扩展实验,通过比较加入不同跨时相数据训练的检测性能变化,评估多时相数据本身对模型识别长期、非线性或缓变地表变化的影响。实验结果表明,多时相遥感影像所包含的时间维度信息在变化检测任务中具有基础性价值,为模型理解地物动态演化提供了新的视角。
未来,数据集将继续扩展至更多地理区域和时间段,并尝试引入光学、SAR、LiDAR等多源遥感模态和语义变化信息,以支持更复杂的多模态变化检测与时序建模研究,进一步推动遥感变化检测方法在跨域与多场景下的应用能力。
支撑本研究的科学数据已在中国科学院科学数据银行ScienceDB平台公开发布,访问地址为https://doi.org/10.57760/sciencedb.j00240.00110。
  • 中国科学院前瞻战略科技先导专项项目(XDA0360303)
参考文献 引证文献
排序方式:
Bandara W G C and Patel V M. 2022. A transformer-based Siamese network for change detection//IGARSS 2022—2022 IEEE International Geoscience and Remote Sensing Symposium. Kuala Lumpur,Malaysia: IEEE: 207-210 [DOI: 10.1109/IGARSS46834.2022.9883686]
Bruzzone L and Prieto D F. 2000. Automatic analysis of the difference image for unsupervised change detection. IEEE Transactions on Geoscience and Remote sensing,38(3): 1171-1182 [DOI: 10.1109/36.843009]
Caye Daudt R,Le Saux B and Boulch A. 2018. Fully convolutional Siamese networks for change detection//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens,Greece: IEEE: 4063-4067 [DOI: 10.1109/ICIP.2018.8451652]
Chen H,Qi Z P and Shi Z W. 2022. Remote sensing image change detection with transformers. IEEE Transactions on Geoscience and Remote Sensing,60: #5607514 [DOI: 10.1109/TGRS.2021.3095166]
Chen H and Shi Z W. 2020. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sensing,12(10): #1662 [DOI: 10.3390/rs12101662]
Chen K Y,Liu C Y,Li W Y,Liu Z L,Chen H,Zhang H T,et al. 2024. Time travelling pixels: bitemporal features integration with foundation model for remote sensing image change detection//IGARSS 2024—2024 IEEE International Geoscience and Remote Sensing Symposium. Athens,Greece: IEEE: 8581-8584 [DOI: 10.1109/IGARSS53475.2024.10640593]
Das S and Angadi D P. 2022. Land use land cover change detection and monitoring of urban growth using remote sensing and GIS techniques: a micro-level study. GeoJournal,87(3): 2101-2123 [DOI: 10.1007/s10708-020-10359-1]
Deng J S,Wang K,Deng Y H and Qi G J. 2008. PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite data. International Journal of Remote Sensing,29(16): 4823-4838 [DOI: 10.1080/01431160801950162]
Du P J,Wang X,Chen D M,Liu S C,Lin C and Meng Y P. 2020. An improved change detection approach using tri-temporal logic-verified change vector analysis. ISPRS Journal of Photogrammetry and Remote Sensing,161: 278-293 [DOI: 10.1016/j.isprsjprs.2020.01.026]
Fang S,Li K Y and Li Z. 2023. Changer: feature interaction is what you need for change detection. IEEE Transactions on Geoscience and Remote Sensing,61: #5610111 [DOI: 10.1109/TGRS.2023.3277496]
Fang S,Li K Y,Shao J Y and Li Z. 2022. SNUNet-CD: a densely connected Siamese network for change detection of VHR images. IEEE Geoscience and Remote Sensing Letters,19: #8007805 [DOI: 10.1109/LGRS.2021.3056416]
Gao Y H,Gao F,Dong J Y and Wang S K. 2019. Transferred deep learning for sea ice change detection from synthetic-aperture radar images. IEEE Geoscience and Remote Sensing Letters,16(10): 1655-1659 [DOI: 10.1109/LGRS.2019.2906279]
Han C X,Wu C,Guo H N,Hu M Q and Chen H R X. 2023. HANet: a hierarchical attention network for change detection with bitemporal very-high-resolution remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,16: 3867-3878 [DOI: 10.1109/JSTARS.2023.3264802]
Ji D Y,Gao S Q,Tao M Y,Lu H T and Zhao F. 2024. Changenet: multi-temporal asymmetric change detection dataset//Proceedings of 2024 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Seoul,Korea(South): IEEE: 2725-2729 [DOI: 10.1109/ICASSP48485.2024.10446592]
Ji S P,Wei S Q and Lu M. 2019. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing,57(1): 574-586 [DOI: 10.1109/TGRS.2018.2858817]
Li K Y,Cao X Y and Meng D Y. 2024. A new learning paradigm for foundation model-based remote-sensing change detection. IEEE Transactions on Geoscience and Remote Sensing,62: #5610112 [DOI: 10.1109/TGRS.2024.3365825]
Li Q Y,Zhong R F,Du X and Du Y. 2022. TransUNetCD: a hybrid transformer network for change detection in optical remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing,60: #5622519 [DOI: 10.1109/TGRS.2022.3169479]
Liu M X,Chai Z Q,Deng H J and Liu R. 2022. A CNN-transformer network with multiscale context aggregation for fine-grained cropland change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,15: 4297-4306 [DOI: 10.1109/JSTARS.2022.3177235]
Lyu H B,Lu H,Mou L C,Li W Y,Wright J,Li X C,et al. 2018. Long-term annual mapping of four cities on different continents by applying a deep information learning method to Landsat data. Remote Sensing,10(3): #471 [DOI: 10.3390/rs10030471]
Lyu Z Y,Lei Z J,Xie L F,Falco N,Shi C and You Z Z. 2024. Novel distribution distance based on inconsistent adaptive region for change detection using hyperspectral remote sensing images. IEEE Transactions on Geoscience and Remote Sensing,62: #4404912 [DOI: 10.1109/TGRS.2024.3378526]
Pang C,Wu J,Ding J,Song C and Xia G S. 2023. Detecting building changes with off-nadir aerial images. Science China Information Sciences,66(4): #140306 [DOI: 10.1007/s11432-022-3691-4]
Saha S,Bovolo F and Bruzzone L. 2018. Destroyed-buildings detection from VHR SAR images using deep features//Proceedings of SPIE 10789,Image and Signal Processing for Remote Sensing XXIV. Berlin,Germany: SPIE: 336-344 [DOI: 10.1117/12.2325149]
Sexton J O,Urban D L,Donohue M J and Song C H. 2013. Long-term land cover dynamics by multi-temporal classification across the Landsat-5 record. Remote Sensing of Environment,128: 246-258 [DOI: 10.1016/j.rse.2012.10.010]
Shen L,Lu Y,Chen H,Wei H,Xie D H,Yue J B,et al. 2021. S2Looking: a satellite side-looking dataset for building change detection. Remote Sensing,13(24): #5094 [DOI: 10.3390/rs13245094]
Shi Q,Liu M X,Li S C,Liu X P,Wang F and Zhang L P. 2022. A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection. IEEE Transactions on Geoscience and Remote Sensing,60: #5604816 [DOI: 10.1109/TGRS.2021.3085870]
Singh A. 1989. Review article digital change detection techniques using remotely-sensed data. International Journal of Remote Sensing,10(6): 989-1003 [DOI: 10.1080/01431168908903939]
Van Etten A and Hogan D. 2021. The SpaceNet multi-temporal urban development challenge//Proceedings of the NeurIPS 2020 Competition and Demonstration Track. Vancouver,Canada: PMLR: 216-232
Wang R F,Yang Z J,Qiu H,Wang F,Gao G and Wu D. 2025. Lightweight change detection network integrating feature interaction and fusion. Journal of Image and Graphics,30(3): 870-882
王仁芳,杨梓健,邱虹,王峰,高广,吴敦. 2025. 结合特征交互和融合的轻量级变化检测网络. 中国图象图形学报,30(3): 870-882 [DOI: 10.11834/jig.240280]
Wang Y H,Gao L R,Chen Z C and Zhang B. 2020. Deep learning and superpixel-based method for high-resolution remote sensing image change detection. Journal of Image and Graphics,25(6): 1271-1282
王艳恒,高连如,陈正超,张兵. 2020. 结合深度学习和超像元的高分遥感影像变化检测. 中国图象图形学报,25(6): 1271-1282 [DOI: 10.11834/jig.190319]
Weismiller R A,Kristof S J,Scholz D K,Anuta P E and Momin S A. 1977. Change detection in coastal zone environments. Photogrammetric Engineering and Remote Sensing,43(12)
Yang K P,Xia G S,Liu Z C,Du B,Yang W,Pelillo M,et al. 2020. Semantic change detection with asymmetric Siamese networks [2025-11-14]. [EB/OL]. https://arxiv.org/pdf/2010.05687.pdf
Zhang C,Wang L J,Cheng S L and Li Y M. 2022. SwinSUNet: pure transformer network for remote sensing image change detection. IEEE Transactions on Geoscience and Remote Sensing,60: #5224713 [DOI: 10.1109/TGRS.2022.3160007]
Zhang C X,Yue P,Tapete D,Jiang L C,Shangguan B Y,Huang L,et al. 2020. A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing,166: 183-200 [DOI: 10.1016/j.isprsjprs.2020.06.003]
Zhang H,Liu W,Niu H,Yin P C,Dong S L,Wu J L,et al. 2024. Land cover change detection based on vector polygons and deep learning with high-resolution remote sensing images. IEEE Transactions on Geoscience and Remote Sensing,62: #4402218 [DOI: 10.1109/TGRS.2023.3346968]
Zhao Y T,Li H C,Lei S,Liu N Q,Pan J and Celik T. 2024. COUD: continual urbanization detector for time series building change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,17: 19601-19615 [DOI: 10.1109/JSTARS.2024.3482559]
Zhu D W,Huang X H,Huang H Y,Zhou H and Shao Z F. 2025. Change3D: revisiting change detection and captioning from a video modeling perspective//Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville,USA: IEEE: 24011-24022 [DOI: 10.1109/CVPR52734.2025.02236]
Zhu Z,Qiu S and Ye S. 2022. Remote sensing of land change: a multifaceted perspective. Remote Sensing of Environment,282: #113266 [DOI: 10.1016/j.rse.2022.113266]
2026年第31卷第10期
PDF下载
52
27
引用本文
BibTeX
文章信息
doi: 10.11834/jig.250563
  • 接收时间:2025-11-14
  • 首发时间:2026-10-30
  • 出版时间:2026-10-16
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-11-14
  • 修回日期:2026-01-30
基金
Strategic Priority Research Program of the Chinese Academy of Sciences(XDA0360303)
中国科学院前瞻战略科技先导专项项目(XDA0360303)
作者信息
    1 中国科学院空天信息创新研究院,北京 100094
    2 中国科学院大学电子电气与通信工程学院,北京 100049
    3 烟台大学物理与电子信息学院,烟台 264005

通讯作者:

陈静波,通信作者,男,研究员,主要研究方向为遥感图像智能解译、资源环境遥感监测应用。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgtxtxxb/CN/10.11834/jig.250563
分享至
全文二维码

扫描看全文

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