DAIS: Deep Learning-Based Detection of Dog-Human-Vehicle Interactions in Urban Surveillance

DAIS: Deep Learning-Based Detection of Dog-Human-Vehicle Interactions in Urban Surveillance | 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 DAIS: Deep Learning-Based Detection of Dog-Human-Vehicle Interactions in Urban Surveillance Pei Xu, Yu-Ting Chin, Chih-Yung Chang, Chin-Hwa Kuo, Diptendu Sinha Roy This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7740260/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 Stray dogs pose increasing public safety concerns in urban environments, often engaging in aggressive behaviors such as chasing pedestrians and vehicles. Traditional animal control approaches are insufficient to handle this growing problem, necessitating intelligent and automated surveillance solutions. This paper introduces a novel deep learning-based framework capable of real-time detection and analysis of interactions among dogs, pedestrians, and vehicles. The proposed system integrates a fine-tuned YOLO-based object detector for accurate recognition of relevant entities, a CNN-based classifier for dog breed identification, and the DeepSORT tracking algorithm enhanced by Kalman filtering for robust multi-object tracking. Additionally, a novel target interaction association algorithm isolates relevant object pairs, while an LSTM-based temporal model classifies interaction sequences to infer aggressive or pursuit behaviors. Experimental evaluations confirm the effectiveness and reliability of the proposed framework, highlighting its potential to significantly improve public safety in urban areas. Artificial Intelligence Deep Learning Multi-Object Tracking Behavior Recognition Interaction Analysis Surveillance Video Analysis 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-7740260","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":566007917,"identity":"244f2412-beac-4ed2-9f0d-db8c1041ace5","order_by":0,"name":"Pei Xu","email":"","orcid":"","institution":"Hefei University","correspondingAuthor":false,"prefix":"","firstName":"Pei","middleName":"","lastName":"Xu","suffix":""},{"id":566007919,"identity":"a1292974-9aa2-4163-9d26-792505c4312c","order_by":1,"name":"Yu-Ting Chin","email":"","orcid":"","institution":"Tamkang University","correspondingAuthor":false,"prefix":"","firstName":"Yu-Ting","middleName":"","lastName":"Chin","suffix":""},{"id":566007923,"identity":"6bc20775-9ad6-4293-9f26-64002d913838","order_by":2,"name":"Chih-Yung Chang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIiWNgGAWjYHACNhAhx8DA2HiAgSEBxDEgSosxUEvDAYYEmJYEwloSG4AEcVr4ZyQ/e/BzR2362vbDDQcYf6QlNrA3b5Ng/HEYpxaJG2nmhr1njuduO5MIclhOYgPPsTIJhgTcWgwkctgkeNuO5W47ANZSkdggkWMG1HIbrxbJv23H0s3OP4RqkX9DWIs0b1tNgtkNmMMkePBrkTjzzExatu2A4bYbQFsS0tKM23jSii0S0v7j1MLfnvxM8m1bnbzZ+fSHDz7YJMv2sx/eeOODTRpOLQwCCSASGj4gNhuMgduaAyCyDp+SUTAKRsEoGOkAAGa3Wr4W/i7EAAAAAElFTkSuQmCC","orcid":"","institution":"Tamkang University","correspondingAuthor":true,"prefix":"","firstName":"Chih-Yung","middleName":"","lastName":"Chang","suffix":""},{"id":566007925,"identity":"be908b2f-742e-49a7-850e-4f9e9b8219e6","order_by":3,"name":"Chin-Hwa Kuo","email":"","orcid":"","institution":"Tamkang University","correspondingAuthor":false,"prefix":"","firstName":"Chin-Hwa","middleName":"","lastName":"Kuo","suffix":""},{"id":566007928,"identity":"18ec102f-df18-4bf0-94f2-b83fce220554","order_by":4,"name":"Diptendu Sinha Roy","email":"","orcid":"","institution":"National Institute of Technology Meghalaya","correspondingAuthor":false,"prefix":"","firstName":"Diptendu","middleName":"Sinha","lastName":"Roy","suffix":""}],"badges":[],"createdAt":"2025-09-29 09:23:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7740260/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7740260/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99153076,"identity":"56508b79-1951-491b-aee9-6d04db0e29bd","added_by":"auto","created_at":"2025-12-29 10:56:44","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2183067,"visible":true,"origin":"","legend":"","description":"","filename":"DAIS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7740260/v1/30e8706b48d14b8e7ad58d21.pdf"},{"id":99153075,"identity":"802fa690-640f-4423-a5ab-85a258511aa2","added_by":"auto","created_at":"2025-12-29 10:56:44","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6253,"visible":true,"origin":"","legend":"","description":"","filename":"dcc8dffda4594bcab9732070699db5e4.json","url":"https://assets-eu.researchsquare.com/files/rs-7740260/v1/bc16f6a0c66a6e35bc06a454.json"},{"id":105728956,"identity":"f823ba40-40e5-443d-a2f3-53663cadfef3","added_by":"auto","created_at":"2026-03-30 11:13:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":761460,"visible":true,"origin":"","legend":"","description":"","filename":"DAIS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7740260/v1_covered_834c6ac3-de71-4ac8-8fca-15a49f05aaf3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DAIS: Deep Learning-Based Detection of Dog-Human-Vehicle Interactions in Urban Surveillance","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Artificial Intelligence, Deep Learning, Multi-Object Tracking, Behavior Recognition,Interaction Analysis , Surveillance Video Analysis","lastPublishedDoi":"10.21203/rs.3.rs-7740260/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7740260/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Stray dogs pose increasing public safety concerns in urban environments, often engaging in aggressive behaviors such as chasing pedestrians and vehicles. Traditional animal control approaches are insufficient to handle this growing problem, necessitating intelligent and automated surveillance solutions. This paper introduces a novel deep learning-based framework capable of real-time detection and analysis of interactions among dogs, pedestrians, and vehicles. The proposed system integrates a fine-tuned YOLO-based object detector for accurate recognition of relevant entities, a CNN-based classifier for dog breed identification, and the DeepSORT tracking algorithm enhanced by Kalman filtering for robust multi-object tracking. Additionally, a novel target interaction association algorithm isolates relevant object pairs, while an LSTM-based temporal model classifies interaction sequences to infer aggressive or pursuit behaviors. Experimental evaluations confirm the effectiveness and reliability of the proposed framework, highlighting its potential to significantly improve public safety in urban areas.","manuscriptTitle":"DAIS: Deep Learning-Based Detection of Dog-Human-Vehicle Interactions in Urban Surveillance","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-29 10:56:40","doi":"10.21203/rs.3.rs-7740260/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":"e0f11f4e-7cf9-4924-8628-6c8bae8c63bf","owner":[],"postedDate":"December 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-30T04:25:23+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-29 10:56:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7740260","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7740260","identity":"rs-7740260","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}