Enhancing Real-Time Object Detection on Low-End Devices: A Comparative Study of Performance of YOLOv4 and SSD MobileNetv2

Enhancing Real-Time Object Detection on Low-End Devices: A Comparative Study of Performance of YOLOv4 and SSD MobileNetv2 | 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 Enhancing Real-Time Object Detection on Low-End Devices: A Comparative Study of Performance of YOLOv4 and SSD MobileNetv2 Ashok Kumar Chimakurthi, Lakshmi Priya Chimakurthy This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4901165/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 research tackles the challenge of achieving efficient and accurate real-time object detection on low-end devices, such as single-board computers and embedded hardware. Departing from the conventional choice of SSD MobileNetv2, the study opts for the YOLOv4 architecture known for its superior performance in both speed and accuracy. By training the model on a dataset consisting of images captured in densely populated public spaces by surveillance cameras, the focus lies on discerning between individuals and crowds, critical for surveillance and crowd management applications. The hardware setup involves deploying the trained model on a Raspberry Pi 3B, a widely accessible single-board computer, to demonstrate real-world feasibility. Beyond merely showcasing improved stability, precision, and accuracy, the research conducts an in-depth analysis encompassing architectural shifts, relevance of training data, inference speed, and resource utilization, aiming to develop machine learning models specifically tailored for low-resource platforms. This holistic approach seeks to strike a balance between computational affordability and real-time performance, ultimately contributing to advancements in surveillance systems for various practical applications. Real-time object detection YOLOv4 architecture low-end devices performance accuracy 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-4901165","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":341824054,"identity":"6cf6b6b4-413e-4ae6-ad80-22b8e34a9e6c","order_by":0,"name":"Ashok Kumar Chimakurthi","email":"data:image/png;base64,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","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Ashok","middleName":"Kumar","lastName":"Chimakurthi","suffix":""},{"id":341824055,"identity":"a371aa6f-9fae-4aa1-aa82-4ec4beea0768","order_by":1,"name":"Lakshmi Priya Chimakurthy","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Lakshmi","middleName":"Priya","lastName":"Chimakurthy","suffix":""}],"badges":[],"createdAt":"2024-08-12 14:17:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4901165/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4901165/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79237323,"identity":"f8f13fee-e829-4adc-8f1f-e926f8b03cdd","added_by":"auto","created_at":"2025-03-26 04:31:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":865296,"visible":true,"origin":"","legend":"","description":"","filename":"PAPER2SP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4901165/v1_covered_5f019263-c1da-4462-8881-613dcadabe50.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Real-Time Object Detection on Low-End Devices: A Comparative Study of Performance of YOLOv4 and SSD MobileNetv2","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":"Real-time object detection, YOLOv4 architecture, low-end devices, performance, accuracy","lastPublishedDoi":"10.21203/rs.3.rs-4901165/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4901165/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis research tackles the challenge of achieving efficient and accurate real-time object detection on low-end devices, such as single-board computers and embedded hardware. Departing from the conventional choice of SSD MobileNetv2, the study opts for the YOLOv4 architecture known for its superior performance in both speed and accuracy. By training the model on a dataset consisting of images captured in densely populated public spaces by surveillance cameras, the focus lies on discerning between individuals and crowds, critical for surveillance and crowd management applications. The hardware setup involves deploying the trained model on a Raspberry Pi 3B, a widely accessible single-board computer, to demonstrate real-world feasibility. Beyond merely showcasing improved stability, precision, and accuracy, the research conducts an in-depth analysis encompassing architectural shifts, relevance of training data, inference speed, and resource utilization, aiming to develop machine learning models specifically tailored for low-resource platforms. This holistic approach seeks to strike a balance between computational affordability and real-time performance, ultimately contributing to advancements in surveillance systems for various practical applications.\u003c/p\u003e","manuscriptTitle":"Enhancing Real-Time Object Detection on Low-End Devices: A Comparative Study of Performance of YOLOv4 and SSD MobileNetv2","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-12 10:43:43","doi":"10.21203/rs.3.rs-4901165/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":"e38e6482-c9eb-43dc-a44a-f9d727267240","owner":[],"postedDate":"September 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-26T04:23:40+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-12 10:43:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4901165","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4901165","identity":"rs-4901165","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}