Deep Learning-Based Animal Footprint Analysis for Species Recognition and Injury Detection

Deep Learning-Based Animal Footprint Analysis for Species Recognition and Injury Detection | 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 Deep Learning-Based Animal Footprint Analysis for Species Recognition and Injury Detection Pranav Bharadwaj This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9667748/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 This study explores a non-invasive way to monitor wildlife through the analysis of animal footprints using deep learning. Traditional tracking methods depend on manual interpretation, which makes them time-consuming, subjective, and difficult to scale across large ecosystems. To address this limitation, we develop a deep learning framework that jointly recognises animal species and identifies injury-related abnormalities from footprint images. A dataset of 1,217 images was compiled from multiple sources, covering six animal species with both normal and injured footprint samples. The task is framed as a fine-grained classification problem, where each class represents both species identity and health condition. Several convolutional neural network architectures, including ResNet-50, EfficientNet, MobileNet-V3, and ConvNeXt, are trained and compared to determine which performs best for this setting. The results indicate that deep learning models are able to capture subtle morphological differences in footprints and achieve strong classification performance, with the best model reaching an overall accuracy of 78.91%. These findings suggest that footprint based analysis can serve as a practical and non-invasive tool for wildlife monitoring and early injury detection, offering a basis for automated health assessment in field conditions. Artificial Intelligence and Machine Learning Wildlife Biology Footprint analysis deep learning injury detection wildlife monitoring Full Text Additional Declarations The authors declare no competing interests. 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-9667748","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":637561488,"identity":"2816968b-62f7-4aed-aa2f-c35ad68b345b","order_by":0,"name":"Pranav Bharadwaj","email":"data:image/png;base64,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","orcid":"","institution":"Independent Researcher","correspondingAuthor":true,"prefix":"","firstName":"Pranav","middleName":"","lastName":"Bharadwaj","suffix":""}],"badges":[],"createdAt":"2026-05-10 05:51:56","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-9667748/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9667748/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109217572,"identity":"afc05309-64d4-49f9-b7a5-349574a8cf5a","added_by":"auto","created_at":"2026-05-13 18:28:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":770098,"visible":true,"origin":"","legend":"","description":"","filename":"ResearchPaperForPrePrintSubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9667748/v1_covered_4a87891c-af67-433f-9036-324169d8d168.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eDeep Learning-Based Animal Footprint Analysis for Species Recognition and Injury Detection\u003c/p\u003e","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":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":"Footprint analysis, deep learning, injury detection, wildlife monitoring","lastPublishedDoi":"10.21203/rs.3.rs-9667748/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9667748/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study explores a non-invasive way to monitor wildlife through the analysis of animal footprints using deep learning. Traditional tracking methods depend on manual interpretation, which makes them time-consuming, subjective, and difficult to scale across large ecosystems. To address this limitation, we develop a deep learning framework that jointly recognises animal species and identifies injury-related abnormalities from footprint images. A dataset of 1,217 images was compiled from multiple sources, covering six animal species with both normal and injured footprint samples. The task is framed as a fine-grained classification problem, where each class represents both species identity and health condition. Several convolutional neural network architectures, including ResNet-50, EfficientNet, MobileNet-V3, and ConvNeXt, are trained and compared to determine which performs best for this setting. The results indicate that deep learning models are able to capture subtle morphological differences in footprints and achieve strong classification performance, with the best model reaching an overall accuracy of 78.91%. These findings suggest that footprint based analysis can serve as a practical and non-invasive tool for wildlife monitoring and early injury detection, offering a basis for automated health assessment in field conditions.\u003c/p\u003e","manuscriptTitle":"Deep Learning-Based Animal Footprint Analysis for Species Recognition and Injury Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-13 18:28:01","doi":"10.21203/rs.3.rs-9667748/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":"e9da30fd-7e88-4a79-8222-9d7f65bd7326","owner":[],"postedDate":"May 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67860711,"name":"Artificial Intelligence and Machine Learning"},{"id":67860712,"name":"Wildlife Biology"}],"tags":[],"updatedAt":"2026-05-13T18:28:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-13 18:28:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9667748","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9667748","identity":"rs-9667748","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}