Identification of Collided Vehicles in Indian Traffic Accidents using Hierarchical Deep Learning Framework

Identification of Collided Vehicles in Indian Traffic Accidents using Hierarchical Deep Learning Framework | 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 Identification of Collided Vehicles in Indian Traffic Accidents using Hierarchical Deep Learning Framework Shrusti Porwal, Yash Khandelwal, Mukul Malik, Preety Singh, Anukriti Bansal This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5664146/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 In Intelligent Transportation Systems (ITS), accurately detecting accidents and identifying the vehicles involved is crucial for assessing accident severity. This paper focuses on the challenge of vehicle identification in accidents on Indian roads. We introduce a hierarchical detection model where an image is first analyzed for accident detection, and if an accident is detected, it is further processed to identify the involved vehicles in collision. We implemented various YOLOv8 model variants for accident and vehicle detection, finding that YOLOv8m performed best with an F1-score of 0.824 for accident detection and 0.827 for vehicle detection. The outputs of these detection units are integrated to identify collided vehicles, achieving an F1-score of 0.716 for this task. vehicle identification accident detection traffic anomaly YOLO 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-5664146","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":392959320,"identity":"6485718f-867c-4d10-b2ef-ff0c13e2d260","order_by":0,"name":"Shrusti Porwal","email":"data:image/png;base64,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","orcid":"","institution":"The LNM Institute of Information Technology, LNMIIT","correspondingAuthor":true,"prefix":"","firstName":"Shrusti","middleName":"","lastName":"Porwal","suffix":""},{"id":392959321,"identity":"899fbfbc-2f28-4897-afc6-adb7e6d3b53c","order_by":1,"name":"Yash Khandelwal","email":"","orcid":"","institution":"The LNM Institute of Information Technology, LNMIIT","correspondingAuthor":false,"prefix":"","firstName":"Yash","middleName":"","lastName":"Khandelwal","suffix":""},{"id":392959322,"identity":"68f50035-ce29-4633-bd31-519045faaaea","order_by":2,"name":"Mukul Malik","email":"","orcid":"","institution":"The LNM Institute of Information Technology, LNMIIT","correspondingAuthor":false,"prefix":"","firstName":"Mukul","middleName":"","lastName":"Malik","suffix":""},{"id":392959323,"identity":"4f821816-3e27-4495-9e65-87fedc85bcc2","order_by":3,"name":"Preety Singh","email":"","orcid":"","institution":"The LNM Institute of Information Technology, LNMIIT","correspondingAuthor":false,"prefix":"","firstName":"Preety","middleName":"","lastName":"Singh","suffix":""},{"id":392959324,"identity":"e6c62721-27b1-41f9-94f2-0f5042ec1315","order_by":4,"name":"Anukriti Bansal","email":"","orcid":"","institution":"The LNM Institute of Information Technology, LNMIIT","correspondingAuthor":false,"prefix":"","firstName":"Anukriti","middleName":"","lastName":"Bansal","suffix":""}],"badges":[],"createdAt":"2024-12-17 18:38:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5664146/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5664146/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":74944084,"identity":"654cf523-66e5-4d4e-9f87-9a4c1d0ba45e","added_by":"auto","created_at":"2025-01-28 15:08:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1223717,"visible":true,"origin":"","legend":"","description":"","filename":"InADmultimediasystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5664146/v1_covered_7ef9d7d7-e910-44ac-9718-116d1a9c567c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Identification of Collided Vehicles in Indian Traffic Accidents using Hierarchical Deep Learning Framework","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":"vehicle identification, accident detection, traffic anomaly, YOLO","lastPublishedDoi":"10.21203/rs.3.rs-5664146/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5664146/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In Intelligent Transportation Systems (ITS), accurately detecting accidents and identifying the vehicles involved is crucial for assessing accident severity. This paper focuses on the challenge of vehicle identification in accidents on Indian roads. We introduce a hierarchical detection model where an image is first analyzed for accident detection, and if an accident is detected, it is further processed to identify the involved vehicles in collision. We implemented various YOLOv8 model variants for accident and vehicle detection, finding that YOLOv8m performed best with an F1-score of 0.824 for accident detection and 0.827 for vehicle detection. The outputs of these detection units are integrated to identify collided vehicles, achieving an F1-score of 0.716 for this task.","manuscriptTitle":"Identification of Collided Vehicles in Indian Traffic Accidents using Hierarchical Deep Learning Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-23 18:16:51","doi":"10.21203/rs.3.rs-5664146/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":"2da88fba-3dee-4e14-908a-31c4bb228b15","owner":[],"postedDate":"December 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-28T15:08:42+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-23 18:16:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5664146","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5664146","identity":"rs-5664146","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}