Vision Transformer-based Change Detection in optical and SAR Remote Sensing Images

Vision Transformer-based Change Detection in optical and SAR Remote Sensing Images | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Vision Transformer-based Change Detection in optical and SAR Remote Sensing Images Emna Brahim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8468332/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Change detection (CD) in remote sensing plays a crucial role in monitoring land cover changes and environmental transformations. Currently, there is a lack of adaptability to different image types. In this work, we propose CD-ViT, an innovative change detection method based on the Vision Transformer (ViT). The proposed framework integrates complementary information from optical and SAR NDVI images through a cross-attention fusion module, followed by a multi-attention UNet decoder to generate highly accurate change maps. Extensive experiments were conducted on several geographical areas, comprising a total of 145,161 patches. Across all studied regions, CD-ViT outperforms state-of-the-art methods, achieving a precision of 94.3% and an F1-score of 94.1%. Change detection Vision Transformer UNet Remote sensing Multi-temporal SAR Optical Deep learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 08 Apr, 2026 Editor assigned by journal 28 Dec, 2025 Submission checks completed at journal 28 Dec, 2025 First submitted to journal 28 Dec, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8468332","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":619370120,"identity":"a68652a6-3e1f-4462-9ef8-b32bf1902e51","order_by":0,"name":"Emna Brahim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYLACxgYGBgNmBsYHJGthNkAWlCCshYGBDUUVTi38YmcPfmDccU/enJ07rfJHRZ28bnsD44ePOQx15ji0SM7OS5ZgPFNsuLOZd9ttnjOHDbedOcAsOXMbg4RlA3YtBrdzDCQY2xIYNxwGamFsO8C47UYCGzMvUIvBAexa7G/nGP8AarEHaSn8+a/Oftv9B/i1GEjnmIFsSQRpYeBtYE7cdoMBvxaJ2zlmFolnEpKBWjZL8xw7nLztTGIz0C8SkhtwaOGfnWN84+OOBNsN589u/Pijps522/HDBz983GbDj8sWMEhA5YKiiUBMjoJRMApGwSjADwDDRFxILNMKgQAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Emna","middleName":"","lastName":"Brahim","suffix":""}],"badges":[],"createdAt":"2025-12-29 01:53:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8468332/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8468332/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106950110,"identity":"d27301f7-4904-49ba-956f-43fa57591953","added_by":"auto","created_at":"2026-04-15 07:19:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":265136,"visible":true,"origin":"","legend":"","description":"","filename":"journal2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8468332/v1_covered_3fc03437-8e0a-4640-ba7b-bdb36c03c9da.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Vision Transformer-based Change Detection in optical and SAR Remote Sensing Images","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Change detection, Vision Transformer, UNet, Remote sensing, Multi-temporal, SAR, Optical, Deep learning","lastPublishedDoi":"10.21203/rs.3.rs-8468332/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8468332/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Change detection (CD) in remote sensing plays a crucial role in monitoring land cover changes and environmental transformations. Currently, there is a lack of adaptability to different image types. In this work, we propose CD-ViT, an innovative change detection method based on the Vision Transformer (ViT). The proposed framework integrates complementary information from optical and SAR NDVI images through a cross-attention fusion module, followed by a multi-attention UNet decoder to generate highly accurate change maps. Extensive experiments were conducted on several geographical areas, comprising a total of 145,161 patches. Across all studied regions, CD-ViT outperforms state-of-the-art methods, achieving a precision of 94.3% and an F1-score of 94.1%.","manuscriptTitle":"Vision Transformer-based Change Detection in optical and SAR Remote Sensing Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-15 07:18:59","doi":"10.21203/rs.3.rs-8468332/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-04-08T05:41:48+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-29T03:41:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-29T03:40:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-12-29T01:34:32+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"22e13e7a-7afa-4d02-bd64-56385254a5e0","owner":[],"postedDate":"April 15th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-15T07:18:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-15 07:18:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8468332","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8468332","identity":"rs-8468332","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}