R-AFPN: A residual asymptotic feature pyramid network for UAV aerial photography of small targets

R-AFPN: A residual asymptotic feature pyramid network for UAV aerial photography of small targets | 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 Article R-AFPN: A residual asymptotic feature pyramid network for UAV aerial photography of small targets Zuowen Chen, Yahong Ma, Zi’an Gong, Minghao Cao, Yuyao Yang, Zhiyuan Wang, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6086930/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 May, 2025 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract This study proposes an improved Residual Asymptotic Feature Pyramid Network (R-AFPN) to address challenges in small target detection from UAV perspectives, such as scale imbalance, feature extraction difficulty, occlusion, and computational constraints. The R-AFPN integrates three key modules: Residual Asymptotic Feature Fusion (RAFF) for adaptive spatial fusion and cross-scale linking, Shallow Information Extraction (SIE) for capturing detailed shallow features, and Hierarchical Feature Fusion (HFF) for bottom-up incremental fusion to enhance deep feature details. Experimental results demonstrate that R-AFPN-L achieves 50.7% AP 50 on the TinyPerson dataset and 48.9% mAP 50 on the VisDrone2019 dataset, outperforming the baseline by 3% and 1.2%, respectively, while reducing parameters by 15.1%. This approach offers a lightweight, efficient solution for small target detection in UAV applications. Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science UAV Small Target Detection Residual Connectivity Asymptotic Feature Fusion Context Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 09 May, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 14 Apr, 2025 Reviews received at journal 13 Apr, 2025 Reviewers agreed at journal 13 Apr, 2025 Reviews received at journal 13 Apr, 2025 Reviewers agreed at journal 10 Apr, 2025 Reviewers agreed at journal 17 Mar, 2025 Reviewers agreed at journal 16 Mar, 2025 Reviewers invited by journal 16 Mar, 2025 Editor assigned by journal 15 Mar, 2025 Editor invited by journal 28 Feb, 2025 Submission checks completed at journal 28 Feb, 2025 First submitted to journal 22 Feb, 2025 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-6086930","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":422470611,"identity":"b2091603-8e36-47cf-be83-f7f30359db86","order_by":0,"name":"Zuowen Chen","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Zuowen","middleName":"","lastName":"Chen","suffix":""},{"id":422470614,"identity":"5891eec9-f3ac-4fe6-993c-2a67555ff125","order_by":1,"name":"Yahong Ma","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYFACHgjFz8DYQKIWyQaStRgcIFaDwfGzBx8X/Nomb3z+cNuDHwx2crqELDM4k5dsPLPvtuG2G4nthj0MycZmhKwzOJBjJs3bc5tx2w3GNgkehgOJ2whqOf8GrMV+c//BNsk/RGm5AbSF58ftxA0MiW3SRNkieeONsTFvw+3kGTeAWmQMiPAL3/kcw8c8f27b9vcffyb5psJOjqAWBZACxja4OwkoBwH5BhD5hwiVo2AUjIJRMHIBAFQKRpVTl7J8AAAAAElFTkSuQmCC","orcid":"","institution":"Xijing University","correspondingAuthor":true,"prefix":"","firstName":"Yahong","middleName":"","lastName":"Ma","suffix":""},{"id":422470616,"identity":"3adbba6f-62c6-4554-9668-6bea5cc4e453","order_by":2,"name":"Zi’an Gong","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Zi’an","middleName":"","lastName":"Gong","suffix":""},{"id":422470619,"identity":"ba3301d6-b9f1-440b-b7dd-876deb3b05ef","order_by":3,"name":"Minghao Cao","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Minghao","middleName":"","lastName":"Cao","suffix":""},{"id":422470622,"identity":"4b12d092-005c-405b-a52b-80232606e5f2","order_by":4,"name":"Yuyao Yang","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Yuyao","middleName":"","lastName":"Yang","suffix":""},{"id":422470624,"identity":"7ac1b460-6f4c-477b-a248-7521ba390f73","order_by":5,"name":"Zhiyuan Wang","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Zhiyuan","middleName":"","lastName":"Wang","suffix":""},{"id":422470626,"identity":"3fe26101-78bb-4a08-ab6a-f843fb757901","order_by":6,"name":"Tengjie Wang","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Tengjie","middleName":"","lastName":"Wang","suffix":""},{"id":422470627,"identity":"2e039dba-3e1a-467c-a4cb-edad8b33f4f0","order_by":7,"name":"Jing Li","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Li","suffix":""},{"id":422470628,"identity":"312e5d23-d1b9-4f71-b513-d94e9a39fe96","order_by":8,"name":"Yuxi Liu","email":"","orcid":"","institution":"Xijing University","correspondingAuthor":false,"prefix":"","firstName":"Yuxi","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-02-22 18:08:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6086930/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6086930/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-00008-3","type":"published","date":"2025-05-09T15:57:51+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":82537771,"identity":"49b5c13e-8d33-46bb-b05c-f1c8a04a61a6","added_by":"auto","created_at":"2025-05-12 16:10:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1486470,"visible":true,"origin":"","legend":"","description":"","filename":"RAFPNsr.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6086930/v1_covered_aa00be93-ec22-430d-bc93-f4e0fda354ae.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"R-AFPN: A residual asymptotic feature pyramid network for UAV aerial photography of small targets","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"UAV, Small Target Detection, Residual Connectivity, Asymptotic Feature Fusion, Context Learning","lastPublishedDoi":"10.21203/rs.3.rs-6086930/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6086930/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e This study proposes an improved Residual Asymptotic Feature Pyramid Network (R-AFPN) to address challenges in small target detection from UAV perspectives, such as scale imbalance, feature extraction difficulty, occlusion, and computational constraints. The R-AFPN integrates three key modules: Residual Asymptotic Feature Fusion (RAFF) for adaptive spatial fusion and cross-scale linking, Shallow Information Extraction (SIE) for capturing detailed shallow features, and Hierarchical Feature Fusion (HFF) for bottom-up incremental fusion to enhance deep feature details. Experimental results demonstrate that R-AFPN-L achieves 50.7% AP\u003csub\u003e50\u003c/sub\u003e on the TinyPerson dataset and 48.9% mAP\u003csub\u003e50\u003c/sub\u003e on the VisDrone2019 dataset, outperforming the baseline by 3% and 1.2%, respectively, while reducing parameters by 15.1%. This approach offers a lightweight, efficient solution for small target detection in UAV applications.\u003c/p\u003e","manuscriptTitle":"R-AFPN: A residual asymptotic feature pyramid network for UAV aerial photography of small targets","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-03 18:00:10","doi":"10.21203/rs.3.rs-6086930/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-14T09:46:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-13T05:25:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"148064874957403049433208407811409108288","date":"2025-04-13T05:23:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-13T04:49:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"244478897030390497359502510915699241781","date":"2025-04-10T17:30:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"48978961690650515108194788179715577454","date":"2025-03-17T04:37:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"213228415183725749326630413749218522185","date":"2025-03-16T15:58:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-03-16T10:49:26+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-15T13:45:28+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-02-28T19:18:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-02-28T07:12:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-02-22T18:01:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"955d56d2-deef-4685-a7ca-4f2c0f628dde","owner":[],"postedDate":"March 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":45036631,"name":"Physical sciences/Mathematics and computing"},{"id":45036632,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-05-12T16:06:46+00:00","versionOfRecord":{"articleIdentity":"rs-6086930","link":"https://doi.org/10.1038/s41598-025-00008-3","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-05-09 15:57:51","publishedOnDateReadable":"May 9th, 2025"},"versionCreatedAt":"2025-03-03 18:00:10","video":"","vorDoi":"10.1038/s41598-025-00008-3","vorDoiUrl":"https://doi.org/10.1038/s41598-025-00008-3","workflowStages":[]},"version":"v1","identity":"rs-6086930","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6086930","identity":"rs-6086930","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}