High Real-Time Multi-Object Tracking Algorithm for Complex Scenarios

High Real-Time Multi-Object Tracking Algorithm for Complex Scenarios | 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 High Real-Time Multi-Object Tracking Algorithm for Complex Scenarios Yufeng Li, Tianyang An, Nairui Hu, Haiyao Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6271854/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Sep, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted 5 You are reading this latest preprint version Abstract In this paper, we propose an enhanced Multi-Object Tracking(MOT) framework based on ByteTrack, achieving dual improvements in efficiency and performance while significantly enhancing robustness in complex scenarios. During the initial matching stage, we integrate an appearance feature matching branch employing a Vmamba backbone network to mitigate occlusion-induced detection failures caused by significant appearance variations. Simultaneously, we introduce a computationally optimized appearance feature extraction method to reduce redundant computational overhead and improve resource utilization. Comprehensive evaluations demonstrate the framework's effectiveness in high-density scenarios, achieving state-of-the-art performance on MOT17 test set with 80.9 MOTA, 79.6 IDF1, and 64.4 HOTA, while maintaining real-time processing at 26.6 FPS. The proposed method also exhibits superior performance on MOT20 benchmark, particularly in addressing severe occlusion challenges and preserving target identity consistency. mot feature fusion computer vision vmamba Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Sep, 2025 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 22 Mar, 2025 Reviewers invited by journal 22 Mar, 2025 Editor assigned by journal 21 Mar, 2025 Submission checks completed at journal 21 Mar, 2025 First submitted to journal 20 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-6271854","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":432589876,"identity":"aa6304c6-095e-4b1e-8aa1-b8114151a845","order_by":0,"name":"Yufeng Li","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Yufeng","middleName":"","lastName":"Li","suffix":""},{"id":432589877,"identity":"d55e06d1-14a8-47b2-80d9-9e679de83094","order_by":1,"name":"Tianyang An","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYBACNmbmww8SKmrk+OUfHyBOCx87W5rBgzPHjCUb0hKI0yLHz6Mg+bCNOXFDQ44BsQ7jYTBIbGNL3MBw5uONNwx2croNBLXwHniQcE7GeDtj72bLOQzJxmYHCGrhSzBIKGOT3dnMu02ah+FA4jbCWngMJBLYmBk3HON5RoqWNmbFDWd42IjVAgzkBFAgz2AztpxjQIRf5PsPH374AxSVEswPb7ypsJMjqAUFSPAQGTXIWkjVMQpGwSgYBSMCAABY/T58ncjvjQAAAABJRU5ErkJggg==","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":true,"prefix":"","firstName":"Tianyang","middleName":"","lastName":"An","suffix":""},{"id":432589878,"identity":"5afd5aeb-0d5c-4de8-acfb-56469e22d1a4","order_by":2,"name":"Nairui Hu","email":"","orcid":"","institution":"Shenyang Aerospace University","correspondingAuthor":false,"prefix":"","firstName":"Nairui","middleName":"","lastName":"Hu","suffix":""},{"id":432589879,"identity":"7e0667ce-c9c7-4df8-be63-c3f1f2c90d17","order_by":3,"name":"Haiyao Wang","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Haiyao","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-03-20 18:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6271854/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6271854/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-025-04748-7","type":"published","date":"2025-09-16T15:57:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":91889783,"identity":"4cb09b6e-81f0-4818-85d4-cc99530b6615","added_by":"auto","created_at":"2025-09-22 16:01:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":536206,"visible":true,"origin":"","legend":"","description":"","filename":"HighRealTimeMultiObjectTrackingAlgorithmforComplexScenarios.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6271854/v1_covered_1600b1b7-9275-484e-b1ec-bd4541157ddf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"High Real-Time Multi-Object Tracking Algorithm for Complex Scenarios","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":"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":"mot, feature fusion, computer vision, vmamba","lastPublishedDoi":"10.21203/rs.3.rs-6271854/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6271854/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In this paper, we propose an enhanced Multi-Object Tracking(MOT) framework based on ByteTrack, achieving dual improvements in efficiency and performance while significantly enhancing robustness in complex scenarios. During the initial matching stage, we integrate an appearance feature matching branch employing a Vmamba backbone network to mitigate occlusion-induced detection failures caused by significant appearance variations. Simultaneously, we introduce a computationally optimized appearance feature extraction method to reduce redundant computational overhead and improve resource utilization. Comprehensive evaluations demonstrate the framework's effectiveness in high-density scenarios, achieving state-of-the-art performance on MOT17 test set with 80.9 MOTA, 79.6 IDF1, and 64.4 HOTA, while maintaining real-time processing at 26.6 FPS. The proposed method also exhibits superior performance on MOT20 benchmark, particularly in addressing severe occlusion challenges and preserving target identity consistency.","manuscriptTitle":"High Real-Time Multi-Object Tracking Algorithm for Complex Scenarios","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-16 04:20:19","doi":"10.21203/rs.3.rs-6271854/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-03-23T01:46:57+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-23T01:46:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-21T08:21:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-21T08:20:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-03-20T18:02:50+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":"cac69131-4f37-4a70-a225-029f3c350287","owner":[],"postedDate":"April 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-22T15:58:56+00:00","versionOfRecord":{"articleIdentity":"rs-6271854","link":"https://doi.org/10.1007/s11760-025-04748-7","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2025-09-16 15:57:12","publishedOnDateReadable":"September 16th, 2025"},"versionCreatedAt":"2025-04-16 04:20:19","video":"","vorDoi":"10.1007/s11760-025-04748-7","vorDoiUrl":"https://doi.org/10.1007/s11760-025-04748-7","workflowStages":[]},"version":"v1","identity":"rs-6271854","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6271854","identity":"rs-6271854","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}