A Hybrid YOLOv5s-Faster R-CNN Architecture for Object Detection in Complex Road Scenes

A Hybrid YOLOv5s-Faster R-CNN Architecture for Object Detection in Complex Road Scenes | 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 A Hybrid YOLOv5s-Faster R-CNN Architecture for Object Detection in Complex Road Scenes Lenard Nkalubo Byenkya, Rose Nakibuule, Danison Taremwa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8559050/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 28 Apr, 2026 Read the published version in Discover Artificial Intelligence → Version 1 posted 12 You are reading this latest preprint version Abstract Accurate and efficient object detection is essential for intelligent road-scene monitoring systems operating in visually complex and resource-constrained environments. While one-stage detectors achieve high inference speed, they often struggle with precise localization of small or low-contrast objects, whereas two-stage detectors provide higher accuracy at the cost of increased latency. To address this trade-off, this paper proposes a hybrid object-detection architecture that integrates You Only Look Once version 5-Small (YOLOv5s) as a fast proposal generator with Faster Region-Based Convolutional Neural Network (Faster R-CNN) as a region-wise refinement module. The proposed framework replaces the Region Proposal Network of Faster R-CNN with high-confidence YOLOv5s detections and employs confidence-weighted fusion to produce spatially consistent final predictions. The hybrid model was evaluated on complex road-scene data using standard object-detection metrics, including mean Average Precision at IoU 0.50 (mAP@50), precision, recall, and inference speed. Experimental results show that the proposed approach achieves mAP@50 of 0.89, improving upon the YOLOv5s baseline by 4.7 percentage points, while maintaining near–real-time performance at 45 frames per second, which is approximately three times faster than a standalone Faster R-CNN. The hybrid detector also attained a precision of 0.93 and a recall of 0.90, demonstrating improved localization accuracy and reduced false detections, particularly for small and visually ambiguous road-scene objects. Repeated experiments confirmed the robustness of the approach, with consistent accuracy gains and low variance across runs. These results demonstrate that strategically combining one-stage and two-stage detection paradigms can yield a favorable accuracy–efficiency balance, making the proposed hybrid architecture suitable for practical deployment in intelligent road-infrastructure and smart-city applications. Object detection Hybrid deep learning YOLOv5s Faster R-CNN Road-scene analysis Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 28 Apr, 2026 Read the published version in Discover Artificial Intelligence → Version 1 posted Editorial decision: Revision requested 19 Feb, 2026 Reviews received at journal 10 Feb, 2026 Reviewers agreed at journal 10 Feb, 2026 Reviews received at journal 27 Jan, 2026 Reviews received at journal 21 Jan, 2026 Reviewers agreed at journal 20 Jan, 2026 Reviewers agreed at journal 20 Jan, 2026 Reviewers invited by journal 20 Jan, 2026 Editor invited by journal 20 Jan, 2026 Editor assigned by journal 09 Jan, 2026 Submission checks completed at journal 09 Jan, 2026 First submitted to journal 09 Jan, 2026 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-8559050","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":577272929,"identity":"48f31fd8-dead-4e18-aabd-e1e25fae4871","order_by":0,"name":"Lenard Nkalubo Byenkya","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIiWNgGAWjYBACPgYGZgaGAoYEBvYGINfAgrAWNrAWA6AWngMgLRKkaJFIAPGJ0cLee9jgh8HhPH7J51c3/CiQYOBv707Ar4XnXHJij8HhYsnZOWU3e4AOkzhzdgN+LRI5xgd4DA4nbridk3aDB6jFQCKXgBb5N8YH/4C03DyTdvMPUVokeIyTwbbcYD92mzhbeHKMjWUM0osle3LYbssYSPAQ9As/+xljyTcV1nn87Mef3Xzzx0aOv70XvxYkwGMAJolVDgLsD0hRPQpGwSgYBSMIAADnxUKqOqhGGAAAAABJRU5ErkJggg==","orcid":"","institution":"Kyambogo University","correspondingAuthor":true,"prefix":"","firstName":"Lenard","middleName":"Nkalubo","lastName":"Byenkya","suffix":""},{"id":577272930,"identity":"e77115d7-92f0-4225-81f3-12d7a5f943ea","order_by":1,"name":"Rose Nakibuule","email":"","orcid":"","institution":"Makerere University","correspondingAuthor":false,"prefix":"","firstName":"Rose","middleName":"","lastName":"Nakibuule","suffix":""},{"id":577272931,"identity":"98c2a596-ff26-4bbc-bdbb-479a547c7ed5","order_by":2,"name":"Danison Taremwa","email":"","orcid":"","institution":"Kyambogo University","correspondingAuthor":false,"prefix":"","firstName":"Danison","middleName":"","lastName":"Taremwa","suffix":""}],"badges":[],"createdAt":"2026-01-09 09:09:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8559050/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8559050/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s44163-026-01253-9","type":"published","date":"2026-04-28T15:57:42+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100858381,"identity":"ec6246f1-f3b3-4b36-9cf8-a4994adc7a5b","added_by":"auto","created_at":"2026-01-22 07:24:14","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3406317,"visible":true,"origin":"","legend":"","description":"","filename":"NkaluboManuscript08012026.docx","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/a736357b16da6a911e811122.docx"},{"id":100831052,"identity":"edb6ac94-47ae-4331-98d8-5d8ed5d743c3","added_by":"auto","created_at":"2026-01-21 21:04:04","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5710,"visible":true,"origin":"","legend":"","description":"","filename":"8111977b6cf54b0c86718fc20bc77670.json","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/99bf853e4f7a4434ed106e11.json"},{"id":100831058,"identity":"38e25916-8697-4653-9ada-d1d845fbf58c","added_by":"auto","created_at":"2026-01-21 21:04:05","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":205293,"visible":true,"origin":"","legend":"","description":"","filename":"8111977b6cf54b0c86718fc20bc776701enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/f8920f12cb3eff27a01e927c.xml"},{"id":100858898,"identity":"7f087ff5-864d-4fea-b4e5-5a1ea8db685f","added_by":"auto","created_at":"2026-01-22 07:24:54","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33112,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/a4055bc7033779ec860c2605.png"},{"id":100859130,"identity":"d905c507-977c-44b7-8704-79aed6f8ed38","added_by":"auto","created_at":"2026-01-22 07:25:20","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":200522,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/bbd1c4313e059173dcad14f5.png"},{"id":100831054,"identity":"ec951adc-fc11-45b3-aa4a-e0cb9662c8e2","added_by":"auto","created_at":"2026-01-21 21:04:05","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70321,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/4e89a8b86dde84f8786ea7b5.png"},{"id":100831051,"identity":"09042a89-8312-4cba-b417-6185ad2edb51","added_by":"auto","created_at":"2026-01-21 21:04:04","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26310,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/a585a2010ccbd7faae824d83.png"},{"id":100831056,"identity":"61218581-421e-449a-a0ee-d7c291f9ca00","added_by":"auto","created_at":"2026-01-21 21:04:05","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41274,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/0bd3dc33252bcf6ab6f9fcaf.png"},{"id":100858560,"identity":"993278fe-8593-4249-a9e9-b565abc749d0","added_by":"auto","created_at":"2026-01-22 07:24:26","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123824,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/c6814362e6956aecef967ab3.png"},{"id":100831059,"identity":"ee17e3cc-5338-4209-983f-9e84d6045d41","added_by":"auto","created_at":"2026-01-21 21:04:05","extension":"xml","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":201860,"visible":true,"origin":"","legend":"","description":"","filename":"8111977b6cf54b0c86718fc20bc776701structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/094e4341d64bef77c124e816.xml"},{"id":100859094,"identity":"1d689f22-d37b-4c07-8b45-5a6ee8addba8","added_by":"auto","created_at":"2026-01-22 07:25:16","extension":"html","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":219921,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1/9cc397a6ecac19e376504321.html"},{"id":108437695,"identity":"356a2f84-e367-4d45-ba61-a86be2eb4310","added_by":"auto","created_at":"2026-05-04 16:02:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":946620,"visible":true,"origin":"","legend":"","description":"","filename":"NkaluboManuscript08012026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8559050/v1_covered_167c428a-3c50-4723-930b-e53fb59e6006.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Hybrid YOLOv5s-Faster R-CNN Architecture for Object Detection in Complex Road Scenes","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Object detection, Hybrid deep learning, YOLOv5s, Faster R-CNN, Road-scene analysis","lastPublishedDoi":"10.21203/rs.3.rs-8559050/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8559050/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate and efficient object detection is essential for intelligent road-scene monitoring systems operating in visually complex and resource-constrained environments. While one-stage detectors achieve high inference speed, they often struggle with precise localization of small or low-contrast objects, whereas two-stage detectors provide higher accuracy at the cost of increased latency. To address this trade-off, this paper proposes a hybrid object-detection architecture that integrates You Only Look Once version 5-Small (YOLOv5s) as a fast proposal generator with Faster Region-Based Convolutional Neural Network (Faster R-CNN) as a region-wise refinement module. The proposed framework replaces the Region Proposal Network of Faster R-CNN with high-confidence YOLOv5s detections and employs confidence-weighted fusion to produce spatially consistent final predictions. The hybrid model was evaluated on complex road-scene data using standard object-detection metrics, including mean Average Precision at IoU 0.50 (mAP@50), precision, recall, and inference speed. Experimental results show that the proposed approach achieves mAP@50 of 0.89, improving upon the YOLOv5s baseline by 4.7 percentage points, while maintaining near\u0026ndash;real-time performance at 45 frames per second, which is approximately three times faster than a standalone Faster R-CNN. The hybrid detector also attained a precision of 0.93 and a recall of 0.90, demonstrating improved localization accuracy and reduced false detections, particularly for small and visually ambiguous road-scene objects. Repeated experiments confirmed the robustness of the approach, with consistent accuracy gains and low variance across runs. These results demonstrate that strategically combining one-stage and two-stage detection paradigms can yield a favorable accuracy\u0026ndash;efficiency balance, making the proposed hybrid architecture suitable for practical deployment in intelligent road-infrastructure and smart-city applications.\u003c/p\u003e","manuscriptTitle":"A Hybrid YOLOv5s-Faster R-CNN Architecture for Object Detection in Complex Road Scenes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-21 21:04:00","doi":"10.21203/rs.3.rs-8559050/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-19T11:08:01+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-11T04:26:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"237526486187565139794661093756349299866","date":"2026-02-11T04:21:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-27T05:00:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-21T10:15:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"238863387068053737128913981719692842331","date":"2026-01-20T07:00:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"43897221474135595154666355035820843816","date":"2026-01-20T06:56:50+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-20T06:37:42+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-20T05:18:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-09T13:22:14+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-09T13:20:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Artificial Intelligence","date":"2026-01-09T08:54:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c7fbfa99-dc7a-4c87-97ba-f17b48c1a944","owner":[],"postedDate":"January 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-05-04T16:00:46+00:00","versionOfRecord":{"articleIdentity":"rs-8559050","link":"https://doi.org/10.1007/s44163-026-01253-9","journal":{"identity":"discover-artificial-intelligence","isVorOnly":false,"title":"Discover Artificial Intelligence"},"publishedOn":"2026-04-28 15:57:42","publishedOnDateReadable":"April 28th, 2026"},"versionCreatedAt":"2026-01-21 21:04:00","video":"","vorDoi":"10.1007/s44163-026-01253-9","vorDoiUrl":"https://doi.org/10.1007/s44163-026-01253-9","workflowStages":[]},"version":"v1","identity":"rs-8559050","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8559050","identity":"rs-8559050","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}