FM-SLAM: A Motion-Aware Visual SLAM Approach for Dynamic Environments Using Fast-SAM and Geometric Consistency

FM-SLAM: A Motion-Aware Visual SLAM Approach for Dynamic Environments Using Fast-SAM and Geometric Consistency | 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 FM-SLAM: A Motion-Aware Visual SLAM Approach for Dynamic Environments Using Fast-SAM and Geometric Consistency Yongchuan Zhang, Yang Qiao, Shan Hu, Jun Xia, Yuexin Lu, Yong Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7164330/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 Accurate visual SLAM in dynamic environments remains a critical challenge due to feature misassociations caused by moving objects. Traditional methods like ORB-SLAM2 often fail to differentiate dynamic and static features, leading to degraded pose estimation and mapping integrity. This paper introduces FM-SLAM, a novel framework that syn-ergizes the zero-shot instance segmentation capability of Fast-SAM with motion-guided geometric consistency checks to eliminate dynamic interference. Unlike prior approaches reliant on semantic priors or manual annotations, FM-SLAM first identifies temporally consistent motion regions using geometric epipolar constraints and refines these regions via Fast-SAM to generate precise dynamic object masks. Feature points within these masked areas are discarded during pose optimization, ensuring robust static feature utilization. Key innovations include: (1) a lightweight, training-free mo-tion-consistency validation strategy that eliminates dependency on prior semantic knowledge, and (2) seamless integration of geometric cues and instance segmentation for enhanced generalizability in unknown environments. Extensive evalua-tions on the TUM RGB-D dataset demonstrate FM-SLAM’s superiority: it achieves 95.76% reduction in absolute trajectory error (ATE) and 93.62% lower relative pose error (RPE) compared to ORB-SLAM2 in high-dynamic sequences. The framework operates in real time at 25 FPS on a single GPU, showcasing practical viability for robotics and augmented real-ity applications. Project page: https://github.com/qiaoyang-adxs/FM-SLAM.git . Dynamic environments instance Segmentation motion consistency check visual SLAM Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 18 Aug, 2025 Editor assigned by journal 31 Jul, 2025 Submission checks completed at journal 23 Jul, 2025 First submitted to journal 19 Jul, 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-7164330","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":503024536,"identity":"03e0aacb-d826-41c2-a886-a1d353dbf5cf","order_by":0,"name":"Yongchuan Zhang","email":"","orcid":"","institution":"Chongqing Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Yongchuan","middleName":"","lastName":"Zhang","suffix":""},{"id":503024537,"identity":"6da9b749-1634-42a4-8f20-de6e9a734e08","order_by":1,"name":"Yang Qiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCUlEQVRIiWNgGAWjYFACxsaHH//YyMkzMzY++ADks7ET1MLcbCzZkGZs2M7cbDgDpIWZoBb2NgnehsOJDOfZ24R5wGYQ0MB3I7FNQnIHcwJjM2Mbs82vbfJ8zAyMHz7m4NYieSOx2aLwDFseOzNj2+PcvtuGbcwMzJIzt+HWYnAjsfGGBBtPMdCWduPcnttAu4De4cWvpUGCh00iseEwY5u0Zc9te2K0NEnwthlAtDD8uJ1IUIvkmYfNxhJnEowNmxmbDXsbbie3MTM24/UL3/H0hw8/VPyXk+c//vDBjz+3bee3Nx/88BGPFoYLCUgcxjYw2YBHPRCcP4DM+4Nf8SgYBaNgFIxMAAAx2lbgOzCMUwAAAABJRU5ErkJggg==","orcid":"","institution":"Chongqing Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Yang","middleName":"","lastName":"Qiao","suffix":""},{"id":503024538,"identity":"cae9fda1-e40e-4d3c-82c9-b9a9daadf2a7","order_by":2,"name":"Shan Hu","email":"","orcid":"","institution":"China Merchants Chongqing Communications Engineering Testing Center Co","correspondingAuthor":false,"prefix":"","firstName":"Shan","middleName":"","lastName":"Hu","suffix":""},{"id":503024539,"identity":"fe268726-202e-42bc-8d4e-349f4593cf11","order_by":3,"name":"Jun Xia","email":"","orcid":"","institution":"Chongqing Academy of Surveying and Mapping","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Xia","suffix":""},{"id":503024540,"identity":"73c143ce-1bc3-4cc2-a7ed-eda5696db782","order_by":4,"name":"Yuexin Lu","email":"","orcid":"","institution":"Chongqing Academy of Surveying and Mapping","correspondingAuthor":false,"prefix":"","firstName":"Yuexin","middleName":"","lastName":"Lu","suffix":""},{"id":503024541,"identity":"91cffd89-da05-476f-aeb7-c86b8a2a5075","order_by":5,"name":"Yong Zhou","email":"","orcid":"","institution":"Chongqing Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Yong","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2025-07-19 12:08:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7164330/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7164330/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89932710,"identity":"31ed4bdb-c8f8-4d77-af74-40be90fed417","added_by":"auto","created_at":"2025-08-26 14:28:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1515523,"visible":true,"origin":"","legend":"","description":"","filename":"FMSLAM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7164330/v1_covered_65e853d0-46b0-46f3-9b60-0e1fca75a65c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"FM-SLAM: A Motion-Aware Visual SLAM Approach for Dynamic Environments Using Fast-SAM and Geometric Consistency","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":"journal-of-intelligent-and-robotic-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of Intelligent \u0026 Robotic Systems](https://link.springer.com/journal/10846)","snPcode":"10846","submissionUrl":"https://submission.springernature.com/new-submission/10846/3","title":"Journal of Intelligent \u0026 Robotic Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Dynamic environments, instance Segmentation, motion consistency check, visual SLAM","lastPublishedDoi":"10.21203/rs.3.rs-7164330/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7164330/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate visual SLAM in dynamic environments remains a critical challenge due to feature misassociations caused by moving objects. Traditional methods like ORB-SLAM2 often fail to differentiate dynamic and static features, leading to degraded pose estimation and mapping integrity. This paper introduces FM-SLAM, a novel framework that syn-ergizes the zero-shot instance segmentation capability of Fast-SAM with motion-guided geometric consistency checks to eliminate dynamic interference. Unlike prior approaches reliant on semantic priors or manual annotations, FM-SLAM first identifies temporally consistent motion regions using geometric epipolar constraints and refines these regions via Fast-SAM to generate precise dynamic object masks. Feature points within these masked areas are discarded during pose optimization, ensuring robust static feature utilization. Key innovations include: (1) a lightweight, training-free mo-tion-consistency validation strategy that eliminates dependency on prior semantic knowledge, and (2) seamless integration of geometric cues and instance segmentation for enhanced generalizability in unknown environments. Extensive evalua-tions on the TUM RGB-D dataset demonstrate FM-SLAM\u0026rsquo;s superiority: it achieves 95.76% reduction in absolute trajectory error (ATE) and 93.62% lower relative pose error (RPE) compared to ORB-SLAM2 in high-dynamic sequences. The framework operates in real time at 25 FPS on a single GPU, showcasing practical viability for robotics and augmented real-ity applications. Project page: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/qiaoyang-adxs/FM-SLAM.git\u003c/span\u003e\u003cspan address=\"https://github.com/qiaoyang-adxs/FM-SLAM.git\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"FM-SLAM: A Motion-Aware Visual SLAM Approach for Dynamic Environments Using Fast-SAM and Geometric Consistency","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-26 14:04:31","doi":"10.21203/rs.3.rs-7164330/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2025-08-18T16:47:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-31T10:58:24+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-23T05:30:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Intelligent \u0026 Robotic Systems","date":"2025-07-19T11:57:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-intelligent-and-robotic-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of Intelligent \u0026 Robotic Systems](https://link.springer.com/journal/10846)","snPcode":"10846","submissionUrl":"https://submission.springernature.com/new-submission/10846/3","title":"Journal of Intelligent \u0026 Robotic Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7485fa2f-ded4-47fa-adad-99da8ccdba74","owner":[],"postedDate":"August 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-08-26T14:04:31+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-26 14:04:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7164330","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7164330","identity":"rs-7164330","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}