Hybrid CNN-Transformer Ensemble for Enhanced Tank Detection in Aerial Imagery

Hybrid CNN-Transformer Ensemble for Enhanced Tank Detection in Aerial Imagery | 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 Hybrid CNN-Transformer Ensemble for Enhanced Tank Detection in Aerial Imagery Yunus Serhat Bıçakçı This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8771811/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 Object detection in unmanned aerial vehicle (UAV) imagery poses significant challenges due to motion blur, occlusion, and unstable viewpoints. This study introduces a hybrid ensemble approach combining transformers' global context modeling with CNNs' local feature extraction capabilities. Validated on the DroneVision benchmark dataset, our method employs Weighted Boxes Fusion (WBF) to integrate predictions from four advanced YOLO variants and a transformer-based detector (RF-DETR). The ensemble achieves superior localization accuracy, outperforming all single-model baselines. Here, we demonstrate that the calibrated fusion of diverse architectural models significantly reduces detection errors in real-world scenarios. All code and trained models are openly available (GitHub: \url{ https://github.com/yunusserhat/drone} ) to facilitate reproducibility, and the UAV tank dataset is accessible through the DroneVision challenge on Kaggle. Aerial vision Drone imagery Object detection RF-DETR Transformer detectors Weighted Boxes Fusion 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-8771811","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":585472434,"identity":"0498441d-e583-4d6a-9db9-874396da3b9f","order_by":0,"name":"Yunus Serhat Bıçakçı","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIiWNgGAWjYFADCSD+gOAyE6WFsXEGihY2IrQ08xCjxeBG7jHJHwx1cuazm58/ts2xy9dtP/vwA0OFdWKDfO8D7Fry0qR5GA4by9w5Zticuy3ZctuZdGMJhjPpiQ1s7AbYteSYSTMwHEicIZEA0sJsYHYgjUGCse0wUAt2l4G0gBxWP0Mi/WOz5bZ6A7Pzz5h/MP7Dr0WCh4E5QUIix7CZcdthA7MbaWwSjA24tUieeWNszWNw2HCGRE7hzN5tx4FanrFZJBxLN25jS8Oqhe94juHNHxV18hIS6Rs+/NxWDXRYGvONDzXWsv3Mx7BqUTgAdh66cAID7piUb8AhMQpGwSgYBaMADgAo4lqYNNahUQAAAABJRU5ErkJggg==","orcid":"","institution":"Marmara University","correspondingAuthor":true,"prefix":"","firstName":"Yunus","middleName":"Serhat","lastName":"Bıçakçı","suffix":""}],"badges":[],"createdAt":"2026-02-03 06:38:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8771811/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8771811/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106993881,"identity":"106821f6-36aa-4f48-8da7-e1c0699cc336","added_by":"auto","created_at":"2026-04-15 14:59:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":528517,"visible":true,"origin":"","legend":"","description":"","filename":"springerthevisualcomputer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8771811/v1_covered_3ab8d689-edcc-4dba-8154-89456e61a02f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Hybrid CNN-Transformer Ensemble for Enhanced Tank Detection in Aerial Imagery","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":"Aerial vision, Drone imagery, Object detection, RF-DETR, Transformer detectors, Weighted Boxes Fusion, YOLO","lastPublishedDoi":"10.21203/rs.3.rs-8771811/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8771811/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Object detection in unmanned aerial vehicle (UAV) imagery poses significant challenges due to motion blur, occlusion, and unstable viewpoints. This study introduces a hybrid ensemble approach combining transformers' global context modeling with CNNs' local feature extraction capabilities. Validated on the DroneVision benchmark dataset, our method employs Weighted Boxes Fusion (WBF) to integrate predictions from four advanced YOLO variants and a transformer-based detector (RF-DETR). The ensemble achieves superior localization accuracy, outperforming all single-model baselines. Here, we demonstrate that the calibrated fusion of diverse architectural models significantly reduces detection errors in real-world scenarios. All code and trained models are openly available (GitHub: \\url{https://github.com/yunusserhat/drone}) to facilitate reproducibility, and the UAV tank dataset is accessible through the DroneVision challenge on Kaggle.","manuscriptTitle":"Hybrid CNN-Transformer Ensemble for Enhanced Tank Detection in Aerial Imagery","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-05 08:39:15","doi":"10.21203/rs.3.rs-8771811/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":"fab297c5-e66a-42fd-bb50-602bd86ab06a","owner":[],"postedDate":"February 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-12T05:39:37+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-05 08:39:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8771811","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8771811","identity":"rs-8771811","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}