Efficient Person Re-Identification via Progressive Filter Pruning and Body Part-Aware Feature Learning

Efficient Person Re-Identification via Progressive Filter Pruning and Body Part-Aware Feature Learning | 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 Efficient Person Re-Identification via Progressive Filter Pruning and Body Part-Aware Feature Learning Anusha Jayasimhan, Vijaya Lakshmi A, Pranaya Padmanabhuni, Priyaadharshini Ramesh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7565672/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 Person re-identification (Re-ID) is a critical task in modern surveillance, enablingthe tracking of individuals across multiple camera views despite variationsin appearance, pose, and background. As public safety demands grow, Re-ID systems must operate efficiently and accurately in real-time, especially onresource-constrained devices. However, traditional deep learning models are oftentoo computationally intensive for practical deployment. This research presents an optimized Re-ID framework that integrates ProgressiveSoft Filter Pruning (PSFP) with local feature learning. PSFP reduces model com-plexity while preserving accuracy, and local feature learning enhances robustnessagainst occlusions and appearance variations. Extensive evaluations on bench-mark datasets demonstrate that the proposed model achieves state-of-the-artaccuracy with significantly reduced inference time, FLOPs, and memory usage.For instance, on the Market-1501 dataset, our method achieves 84.61% Rank-1accuracy, with a 37% reduction in FLOPs and a 16.7% decrease in memory usagecompared to the baseline. These results confirm the feasibility of lightweight, scalable Re-ID solutionsfor public safety and autonomous systems, while also supporting the ethi-cal and sustainability goals of energy-efficient AI for smart city environments.The complete implementation is available at https://github.com/women-ssniffp/Person-ReID-PSFP.git. model compression machine vision occlusion filter pruning 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-7565672","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":514246832,"identity":"879ba73c-4a51-4739-9728-9e0a7f094973","order_by":0,"name":"Anusha Jayasimhan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYJACZgYGNjkIkw2MiNNiTLIWhsQGmBaCgH92j/Hnghq+9Pn9Zw8wfCg7zMAn3YBfi8SdM2bSM46x5W64kZfAOOPcYQY2mQMErLmRY8bMwwbUIsFjwMzbBtQikYBfh/yNHOPPPP/Y0uX7zxgw/yVGi8GNHANp3ja2BIYDOQbMjMRoMbyRVibN28dmuAGo92DPuXQeglrkbiRv/szz7Zg80GGGD36UWcvJzyCgBQqOgckDQMxDlHogqCFW4SgYBaNgFIxEAAAcHDuAazFIPwAAAABJRU5ErkJggg==","orcid":"","institution":"Sri Sivasubramaniya Nadar College of Engineering","correspondingAuthor":true,"prefix":"","firstName":"Anusha","middleName":"","lastName":"Jayasimhan","suffix":""},{"id":514246833,"identity":"63e508ab-1244-4e44-b831-36a70ba5e6b1","order_by":1,"name":"Vijaya Lakshmi A","email":"","orcid":"","institution":"Sri Sivasubramaniya Nadar College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Vijaya","middleName":"Lakshmi","lastName":"A","suffix":""},{"id":514246834,"identity":"7fae337d-52d9-4f65-b010-c8793e20fb1a","order_by":2,"name":"Pranaya Padmanabhuni","email":"","orcid":"","institution":"Sri Sivasubramaniya Nadar College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Pranaya","middleName":"","lastName":"Padmanabhuni","suffix":""},{"id":514246835,"identity":"655f77d0-ab2a-466d-9e0d-fbda585787be","order_by":3,"name":"Priyaadharshini Ramesh","email":"","orcid":"","institution":"Sri Sivasubramaniya Nadar College of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Priyaadharshini","middleName":"","lastName":"Ramesh","suffix":""}],"badges":[],"createdAt":"2025-09-08 15:08:22","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7565672/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7565672/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92910336,"identity":"6e97538c-a940-4ad3-8923-07ca2dede966","added_by":"auto","created_at":"2025-10-07 03:13:03","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5873,"visible":true,"origin":"","legend":"","description":"","filename":"10c99f794199432199f92723172e4111.json","url":"https://assets-eu.researchsquare.com/files/rs-7565672/v1/0f48cea2acd5b4316e920cb0.json"},{"id":93596109,"identity":"55f796f9-c967-4c7c-b8b3-649ebe589597","added_by":"auto","created_at":"2025-10-15 13:47:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":957880,"visible":true,"origin":"","legend":"","description":"","filename":"PERSONREIDSPRINGERTEMPLATE.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7565672/v1_covered_92963e81-baf8-49a8-9bd8-5f6826e31327.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Efficient Person Re-Identification via Progressive Filter Pruning and Body Part-Aware Feature Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"model compression, machine vision, occlusion, filter pruning","lastPublishedDoi":"10.21203/rs.3.rs-7565672/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7565672/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePerson re-identification (Re-ID) is a critical task in modern surveillance, enablingthe tracking of individuals across multiple camera views despite variationsin appearance, pose, and background. As public safety demands grow, Re-ID systems must operate efficiently and accurately in real-time, especially onresource-constrained devices. However, traditional deep learning models are oftentoo computationally intensive for practical deployment.\u003c/p\u003e\n\u003cp\u003eThis research presents an optimized Re-ID framework that integrates ProgressiveSoft Filter Pruning (PSFP) with local feature learning. PSFP reduces model com-plexity while preserving accuracy, and local feature learning enhances robustnessagainst occlusions and appearance variations. Extensive evaluations on bench-mark datasets demonstrate that the proposed model achieves state-of-the-artaccuracy with significantly reduced inference time, FLOPs, and memory usage.For instance, on the Market-1501 dataset, our method achieves 84.61% Rank-1accuracy, with a 37% reduction in FLOPs and a 16.7% decrease in memory usagecompared to the baseline.\u003c/p\u003e\n\u003cp\u003eThese results confirm the feasibility of lightweight, scalable Re-ID solutionsfor public safety and autonomous systems, while also supporting the ethi-cal and sustainability goals of energy-efficient AI for smart city environments.The complete implementation is available at https://github.com/women-ssniffp/Person-ReID-PSFP.git.\u003c/p\u003e","manuscriptTitle":"Efficient Person Re-Identification via Progressive Filter Pruning and Body Part-Aware Feature Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-07 03:12:58","doi":"10.21203/rs.3.rs-7565672/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":"cdb01bc6-2a76-43cf-a158-653c5e82d9a0","owner":[],"postedDate":"October 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-15T13:39:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-07 03:12:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7565672","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7565672","identity":"rs-7565672","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}