Real-time RGBT tracking via isometric feature encoding networking

Real-time RGBT tracking via isometric feature encoding networking | 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 Real-time RGBT tracking via isometric feature encoding networking Zhao Gao, Dongming Zhou, Kaixiang Yan, Yisong Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4824842/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Nov, 2024 Read the published version in Signal, Image and Video Processing → Version 1 posted 6 You are reading this latest preprint version Abstract To efficiently utilize the complementary attributes in RGBT images, we proposes an object tracking algorithm called Isomeric Feature Encoding Network (IFENet). Based on the different characteristics of RGBT images, IFENet employs the global-memory enhancement (GME) in the early stage of image feature encoding to explore detailed information (such as texture and color) in the RGB modality. It also utilizes the border-region salience enhancement (BRE) to improve the saliency difference between the object region and the background. Furthermore, an interest region sampling is introduced to reduce computational consumption and improve the operational efficiency. Validation results on the open-source datasets demonstrate the effectiveness of IFENet. Compared to current mainstream RGBT tracking algorithms, IFENet achieves better tracking accuracy and robustness. It can effectively handle challenging scenarios such as fast-moving objects, large-scale deformations, and camera motion. Moreover, IFENet achieves an average tracking speed of 62FPS, meeting real-time tracking requirements. isomeric feature dual-modality RGBT tracking Real-time tracking Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 30 Nov, 2024 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 01 Sep, 2024 Reviewers agreed at journal 07 Aug, 2024 Reviewers invited by journal 06 Aug, 2024 Editor assigned by journal 30 Jul, 2024 Submission checks completed at journal 30 Jul, 2024 First submitted to journal 29 Jul, 2024 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-4824842","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":341569192,"identity":"ca44e9df-4a33-4ee0-9fa3-a3ca0edcbe9f","order_by":0,"name":"Zhao Gao","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Zhao","middleName":"","lastName":"Gao","suffix":""},{"id":341569193,"identity":"96e6f620-02d7-4300-8070-321ba0e2d33e","order_by":1,"name":"Dongming Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYDACCSDmYbCBcHhI0JJGupbDJGiRn918TOJtzvnE7RIJjA/etjHImxPSwjjnWJrk3G23E3fOSGA2nNvGYLizgYAWZokcM2leoJYNNxLYpHnbGBIMDhDQwgbRcg6khf03UVp4IFoOgG1hJkqLhERasuXcbcnGG848bJacc07CcAMhLfIzkg/eeLvNTnbD8eSDH96U2cgTtAUGHBsYGBsYINFEJLAnXukoGAWjYBSMOAAASzM+BQySq5MAAAAASUVORK5CYII=","orcid":"","institution":"Yunnan University","correspondingAuthor":true,"prefix":"","firstName":"Dongming","middleName":"","lastName":"Zhou","suffix":""},{"id":341569194,"identity":"cc7a4f38-a976-464c-8c73-83f9af1c9d36","order_by":2,"name":"Kaixiang Yan","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Kaixiang","middleName":"","lastName":"Yan","suffix":""},{"id":341569195,"identity":"3b0dfea9-9d51-4d4f-8833-3e46ee4e5418","order_by":3,"name":"Yisong Liu","email":"","orcid":"","institution":"Yunnan University","correspondingAuthor":false,"prefix":"","firstName":"Yisong","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2024-07-30 01:15:54","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4824842/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4824842/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-024-03658-4","type":"published","date":"2024-11-30T15:58:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":70382843,"identity":"b80447ef-8017-412c-87cf-36b51f9291ed","added_by":"auto","created_at":"2024-12-02 16:33:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":631978,"visible":true,"origin":"","legend":"","description":"","filename":"RealtimeRGBTtrackingviaisometricfeatureencodingnetworking.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4824842/v1_covered_4de73ceb-3d68-4f8b-9c0a-49fc37dac62a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Real-time RGBT tracking via isometric feature encoding networking","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":"isomeric feature, dual-modality, RGBT tracking, Real-time tracking","lastPublishedDoi":"10.21203/rs.3.rs-4824842/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4824842/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo efficiently utilize the complementary attributes in RGBT images, we proposes an object tracking algorithm called Isomeric Feature Encoding Network (IFENet). Based on the different characteristics of RGBT images, IFENet employs the global-memory enhancement (GME) in the early stage of image feature encoding to explore detailed information (such as texture and color) in the RGB modality. It also utilizes the border-region salience enhancement (BRE) to improve the saliency difference between the object region and the background. Furthermore, an interest region sampling is introduced to reduce computational consumption and improve the operational efficiency. Validation results on the open-source datasets demonstrate the effectiveness of IFENet. Compared to current mainstream RGBT tracking algorithms, IFENet achieves better tracking accuracy and robustness. It can effectively handle challenging scenarios such as fast-moving objects, large-scale deformations, and camera motion. Moreover, IFENet achieves an average tracking speed of 62FPS, meeting real-time tracking requirements.\u003c/p\u003e","manuscriptTitle":"Real-time RGBT tracking via isometric feature encoding networking","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-26 03:29:05","doi":"10.21203/rs.3.rs-4824842/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-01T15:35:18+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"324916746120359995372199496122801441568","date":"2024-08-07T09:49:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-07T01:41:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-30T09:54:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-30T09:52:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-07-30T01:14:34+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":"fabafe5a-9e7a-468a-ba36-f3b15cf9ad99","owner":[],"postedDate":"August 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-02T16:04:26+00:00","versionOfRecord":{"articleIdentity":"rs-4824842","link":"https://doi.org/10.1007/s11760-024-03658-4","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2024-11-30 15:58:00","publishedOnDateReadable":"November 30th, 2024"},"versionCreatedAt":"2024-08-26 03:29:05","video":"","vorDoi":"10.1007/s11760-024-03658-4","vorDoiUrl":"https://doi.org/10.1007/s11760-024-03658-4","workflowStages":[]},"version":"v1","identity":"rs-4824842","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4824842","identity":"rs-4824842","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}