Two-Stage Cascaded Vision Transformer with Spatial Attention for Dense Settlement Detection in Remote Sensing Imagery

Two-Stage Cascaded Vision Transformer with Spatial Attention for Dense Settlement Detection in Remote Sensing Imagery | 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 Article Two-Stage Cascaded Vision Transformer with Spatial Attention for Dense Settlement Detection in Remote Sensing Imagery Qi Zhong, Jun Luo, Jingxin Fang, Yi Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5514918/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 May, 2025 Read the published version in npj Heritage Science → Version 1 posted 7 You are reading this latest preprint version Abstract Remote sensing is indispensable for studying traditional settlements in geographically inaccessible regions, however, dense settlement detection faces two challenges: spectral/textural similarity leads to redundant features that obscure macro-scale patterns, and fragmented structures impede fine-grained attribute extraction. To address these critical issues, this study proposes a novel two-stage cascaded network designed for capturing both global and local features. In Stage I, a Vision Transformer (SA-ViT) with integrated spatial attention and learnable gating extracts global features, discerning settlement-level patterns. Stage II employs a cascaded pyramid feature aggregation network with residual convolution modules to enhance feature reuse, enabling refined extraction of individual buildings and their attributes. When validated on Qiang villages in China, our framework achieves 98.1% settlement recognition accuracy and 94.4% precision in detecting architectural attributes. In addressing dense scene complexities, this framework significantly enhances remote sensing detection capabilities and contributes to the advancement of traditional settlement studies and cultural heritage preservation. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 May, 2025 Read the published version in npj Heritage Science → Version 1 posted Editorial decision: Accepted 09 May, 2025 Reviews received at journal 16 Apr, 2025 Reviewers agreed at journal 15 Apr, 2025 Reviewers agreed at journal 15 Apr, 2025 Reviewers invited by journal 15 Apr, 2025 Submission checks completed at journal 14 Apr, 2025 First submitted to journal 14 Mar, 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-5514918","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":447419366,"identity":"cb827b27-169b-447d-8d60-b3220d0a4020","order_by":0,"name":"Qi Zhong","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Zhong","suffix":""},{"id":447419367,"identity":"ed35e84f-491c-40b5-b4e4-60861b22c21c","order_by":1,"name":"Jun Luo","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Luo","suffix":""},{"id":447419368,"identity":"006dac2b-ad7d-4fa2-a1f0-508a7052eadb","order_by":2,"name":"Jingxin Fang","email":"","orcid":"","institution":"Sichuan University","correspondingAuthor":false,"prefix":"","firstName":"Jingxin","middleName":"","lastName":"Fang","suffix":""},{"id":447419369,"identity":"a2544322-21eb-4daf-8527-9f8e463c2dfb","order_by":3,"name":"Yi Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYDACCRBhwMBswMDA+AAilEC8FhAmWgtYFwObBFFa+Gc3H3vMU8DAbi6RY1b5o+YwAz97jgHDzx14LLlzLN2YB+gwy54zZrd5jh1mkOx5Y8DYewa3FgOg4dIgLQbHe8xuMzYcZjC4kWPAzNiGT0v+N4iWwzxmhT+BWuwJa8lhg9vCwAuyRYKAFokbaWaSc0BazhwrluY5ls4jceZZwcFePFr4ZyQ/k3jzhyHZ4Ebyxo8/aqzl+NuTNz74iUcLCDDxMPxPZmDgAMckD4g4gF8DMKH8YGCwY2Bgf0BI4SgYBaNgFIxQAABNr0etYjvblAAAAABJRU5ErkJggg==","orcid":"","institution":"Sichuan University","correspondingAuthor":true,"prefix":"","firstName":"Yi","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2024-11-24 16:23:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5514918/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5514918/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s40494-025-01787-8","type":"published","date":"2025-05-23T15:58:26+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":83460669,"identity":"c19236c8-2038-4228-849b-072fd1f7fe5b","added_by":"auto","created_at":"2025-05-26 16:13:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1980505,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedManuscriptFile.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5514918/v1_covered_968ddede-57e4-4848-90f7-f95e055395e7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Two-Stage Cascaded Vision Transformer with Spatial Attention for Dense Settlement Detection in Remote Sensing Imagery","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5514918/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5514918/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRemote sensing is indispensable for studying traditional settlements in geographically inaccessible regions, however, dense settlement detection faces two challenges: spectral/textural similarity leads to redundant features that obscure macro-scale patterns, and fragmented structures impede fine-grained attribute extraction.\u003c/p\u003e \u003cp\u003eTo address these critical issues, this study proposes a novel two-stage cascaded network designed for capturing both global and local features. In Stage I, a Vision Transformer (SA-ViT) with integrated spatial attention and learnable gating extracts global features, discerning settlement-level patterns. Stage II employs a cascaded pyramid feature aggregation network with residual convolution modules to enhance feature reuse, enabling refined extraction of individual buildings and their attributes. When validated on Qiang villages in China, our framework achieves 98.1% settlement recognition accuracy and 94.4% precision in detecting architectural attributes. In addressing dense scene complexities, this framework significantly enhances remote sensing detection capabilities and contributes to the advancement of traditional settlement studies and cultural heritage preservation.\u003c/p\u003e","manuscriptTitle":"Two-Stage Cascaded Vision Transformer with Spatial Attention for Dense Settlement Detection in Remote Sensing Imagery","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-28 08:16:50","doi":"10.21203/rs.3.rs-5514918/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-05-09T20:20:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-16T04:58:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"27334859894804363452117097524865518672","date":"2025-04-16T00:08:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"85582384194704721778613143843429405901","date":"2025-04-15T23:41:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-15T21:44:01+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-15T01:29:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"Heritage Science","date":"2025-03-14T17:48:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"055f04a3-5d3d-409f-ba21-5797b8c476c0","owner":[],"postedDate":"April 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-05-26T16:10:37+00:00","versionOfRecord":{"articleIdentity":"rs-5514918","link":"https://doi.org/10.1038/s40494-025-01787-8","journal":{"identity":"npj-heritage-science","isVorOnly":false,"title":"npj Heritage Science"},"publishedOn":"2025-05-23 15:58:26","publishedOnDateReadable":"May 23rd, 2025"},"versionCreatedAt":"2025-04-28 08:16:50","video":"","vorDoi":"10.1038/s40494-025-01787-8","vorDoiUrl":"https://doi.org/10.1038/s40494-025-01787-8","workflowStages":[]},"version":"v1","identity":"rs-5514918","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5514918","identity":"rs-5514918","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}