Construction of a Remote Sensing Image Training Set for Rail Transit Protection Zones in Megacities and Evaluation of Building Identification Accuracy

Construction of a Remote Sensing Image Training Set for Rail Transit Protection Zones in Megacities and Evaluation of Building Identification Accuracy | 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 Construction of a Remote Sensing Image Training Set for Rail Transit Protection Zones in Megacities and Evaluation of Building Identification Accuracy Chengyang Qian, Long Zhao, Peilin Ni, Yu Zhang, Zini Cao, Cai Jia This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4975893/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract With the acceleration of urbanization in China, rail transit has increasingly become a crucial part of the transportation system. However, construction activities such as pit construction, new construction, or demolition of buildings in rail transit protection zones pose a substantial threat to structural safety. Efficiently monitoring and managing changes in buildings within these zones has become a hot spot in current research. Presently, academics are predominantly concentrating on the iteration and optimization of deep learning algorithms for building recognition and achieving fruitful results. Nevertheless, there is still a lack of evaluation on the effectiveness of the identical deep learning algorithm on different sample sets. Consequently, this paper selects the protection zones of 16 lines under the Beijing Subway Operation Co., Ltd. and employs the Mask R-CNN algorithm to identify and extract building changes. The study utilizes two general datasets and a dedicated training sample set for quantitative analysis and evaluation of effectiveness. Results demonstrate that the Mask R-CNN algorithm, with the dedicated training sample set, achieves superior performance in all metrics. The P reaches 92.45%, showing a significant improvement compared to the general datasets. The R is 93.28%, with a relatively smaller improvement. The F1 score and IOU are 92.86% and 86.38%, respectively, which are significantly higher than those of the general datasets. Furthermore, compared to the advanced building change detection algorithm EGRCNN, the R is 1.06% lower. However, other indicators show improvements, with increases of 1.04%, 3.62%, and 5.81%, correspondingly. Earth and environmental sciences/Environmental sciences Physical sciences/Engineering Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4975893","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":361264018,"identity":"ab238737-06b4-4a05-aace-fc1160cb96be","order_by":0,"name":"Chengyang Qian","email":"","orcid":"","institution":"Jiangsu Geospatial Artificial Intelligence Engineering Research Center","correspondingAuthor":false,"prefix":"","firstName":"Chengyang","middleName":"","lastName":"Qian","suffix":""},{"id":361264019,"identity":"edb54c76-c126-4e5f-a890-674c94214fa1","order_by":1,"name":"Long Zhao","email":"","orcid":"","institution":"School of Geography and Tourism, Anhui Normal University","correspondingAuthor":false,"prefix":"","firstName":"Long","middleName":"","lastName":"Zhao","suffix":""},{"id":361264020,"identity":"a7f8e868-bb7c-4913-88e6-7591ec773b6a","order_by":2,"name":"Peilin Ni","email":"","orcid":"","institution":"SIPSG Information Technology Co. Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Peilin","middleName":"","lastName":"Ni","suffix":""},{"id":361264021,"identity":"fe366675-a7da-4149-9075-af1fc0448383","order_by":3,"name":"Yu Zhang","email":"","orcid":"","institution":"SIPSG Information Technology Co. Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhang","suffix":""},{"id":361264022,"identity":"1948e1c5-a0fa-47a5-9946-61ff6e1bb646","order_by":4,"name":"Zini Cao","email":"","orcid":"","institution":"School of Geography and Tourism, Anhui Normal University","correspondingAuthor":false,"prefix":"","firstName":"Zini","middleName":"","lastName":"Cao","suffix":""},{"id":361264023,"identity":"4fe35865-f942-4875-a5e3-54d6e807853d","order_by":5,"name":"Cai Jia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAx0lEQVRIiWNgGAWjYBAC+2b+5z8+VEjYsbE3EKnFgJ2HQXLGGYtkPp4DxGrh52GQ5myrYJwnkUCkFnNm3gPGjG0SzGySjzfeYKixiSaoxbKZLyG54JwEH5t0WrEFw7G03AaCeg4zGByeUQa0RTrHTIKx4TBRWgybedgkGNskzxCpxeAwjzEzTxtQiwQPkVokm9nSGGeckUhm4wH6JYEYv/DzHz7G8KGizk6+/fDGGx9qbIjwC7IjiY4aJC2k6hgFo2AUjIKRAQC1nTextUDm1wAAAABJRU5ErkJggg==","orcid":"","institution":"School of Geography and Tourism, Anhui Normal University","correspondingAuthor":true,"prefix":"","firstName":"Cai","middleName":"","lastName":"Jia","suffix":""}],"badges":[],"createdAt":"2024-08-26 07:11:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4975893/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4975893/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":66921784,"identity":"5ef99d31-fb25-4f14-b949-de59589e6437","added_by":"auto","created_at":"2024-10-18 04:47:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1374866,"visible":true,"origin":"","legend":"","description":"","filename":"ConstructionofaRemoteSensingImageTrainingSetforRailTransitProtectionZonesinMegacitiesandEvaluationofBuildingIdentificationAccuracy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4975893/v1_covered_b645af7a-5093-496b-93b0-0eec5c1dbce1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Construction of a Remote Sensing Image Training Set for Rail Transit Protection Zones in Megacities and Evaluation of Building Identification Accuracy","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4975893/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4975893/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWith the acceleration of urbanization in China, rail transit has increasingly become a crucial part of the transportation system. However, construction activities such as pit construction, new construction, or demolition of buildings in rail transit protection zones pose a substantial threat to structural safety. Efficiently monitoring and managing changes in buildings within these zones has become a hot spot in current research. Presently, academics are predominantly concentrating on the iteration and optimization of deep learning algorithms for building recognition and achieving fruitful results. Nevertheless, there is still a lack of evaluation on the effectiveness of the identical deep learning algorithm on different sample sets. Consequently, this paper selects the protection zones of 16 lines under the Beijing Subway Operation Co., Ltd. and employs the Mask R-CNN algorithm to identify and extract building changes. The study utilizes two general datasets and a dedicated training sample set for quantitative analysis and evaluation of effectiveness. Results demonstrate that the Mask R-CNN algorithm, with the dedicated training sample set, achieves superior performance in all metrics. The P reaches 92.45%, showing a significant improvement compared to the general datasets. The R is 93.28%, with a relatively smaller improvement. The F1 score and IOU are 92.86% and 86.38%, respectively, which are significantly higher than those of the general datasets. Furthermore, compared to the advanced building change detection algorithm EGRCNN, the R is 1.06% lower. However, other indicators show improvements, with increases of 1.04%, 3.62%, and 5.81%, correspondingly.\u003c/p\u003e","manuscriptTitle":"Construction of a Remote Sensing Image Training Set for Rail Transit Protection Zones in Megacities and Evaluation of Building Identification Accuracy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-04 07:57:22","doi":"10.21203/rs.3.rs-4975893/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4314258e-4342-4ee0-9650-9f8da3abd7cd","owner":[],"postedDate":"October 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":38437212,"name":"Earth and environmental sciences/Environmental sciences"},{"id":38437213,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2024-10-18T04:39:03+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-04 07:57:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4975893","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4975893","identity":"rs-4975893","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}