YOLO-MAFD: A Collaborative Detection Framework for Automated Recognition of Bridge Steel Structural Components

YOLO-MAFD: A Collaborative Detection Framework for Automated Recognition of Bridge Steel Structural Components | 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 YOLO-MAFD: A Collaborative Detection Framework for Automated Recognition of Bridge Steel Structural Components Guixiang Xue, Jiaxiang Li, Changhai Xu, Junfei Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9251730/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 Automatic recognition of bridge steel structural components is crucial for intelligent bridge inspection and structural assessment. This study addresses a four-class detection task involving bearings, out-of-plane stiffeners (OPS), gusset plate connections (GPC), and cover plate terminations (CPT) in complex bridge scenes. Although YOLOv8 provides an efficient detection framework, its performance is limited by insufficient discriminative feature extraction, information loss during multi-scale fusion, and instability in classification and localization under background interference and class similarity. To address these limitations, a collaborative detection architecture, termed YOLO-MAFD, is proposed by introducing an attention-enhanced convolution module into the backbone, an optimized multi-scale feature fusion strategy into the neck, and an improved decoupled prediction head. Experimental results show that the proposed method outperforms the baseline YOLOv8 model, achieving an [email protected] of 0.766, corresponding to a 9.4% relative improvement, while also improving [email protected] :0.95 and Recall. These results demonstrate that the proposed method improves the accuracy and robustness of bridge steel structural component detection, particularly under complex backgrounds and multi-class interference. YOLOv8 bridge inspection structural component detection attention mechanism multi-scale feature fusion 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-9251730","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":615406199,"identity":"5407172f-4900-41d0-b5ca-d496050ef00f","order_by":0,"name":"Guixiang Xue","email":"","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Guixiang","middleName":"","lastName":"Xue","suffix":""},{"id":615406200,"identity":"30518faa-d391-4118-936d-7e4b97636020","order_by":1,"name":"Jiaxiang Li","email":"","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jiaxiang","middleName":"","lastName":"Li","suffix":""},{"id":615406201,"identity":"707fa531-5045-494a-85af-02dd00d3d180","order_by":2,"name":"Changhai Xu","email":"","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Changhai","middleName":"","lastName":"Xu","suffix":""},{"id":615406202,"identity":"2b4d85e9-5d13-4ee0-8d2b-0951ba24b348","order_by":3,"name":"Junfei Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYBACxgYGhg8MBgwJIPZjBoYDYFEJAloYZ0C1MBuDtPAQ0gLSNQNIgLSwSROlhXlG7sGGDwV1efyz269VF1TcSdzPwHzwNg+DXR5uK/ISG2cYsBVL3DlTdnvGmWeJPQxsydY8DMnFuLXkmD/mMeBJbLiRk3abt+0wUAuPmTQPw4HEBtxaDJv/GEgkzgdqKeb9B9LC/42wFgYDg8QNN9KPMfM2gG1hw6+l541hY49BQuLGGznM0jzHnhn3HGYztpxjkIxTi2F7jmHDjz91ifNupD/8zFNzR7a9vfnhjTcVdri1ICR4DCA0M4gwwKEeCOQRTPYHuJWNglEwCkbBiAYAaYtcE3QRMV8AAAAASUVORK5CYII=","orcid":"","institution":"Hebei University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Junfei","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-03-28 10:08:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9251730/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9251730/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108823241,"identity":"3c43e4c4-aab7-4bc8-a767-3d00aa25390b","added_by":"auto","created_at":"2026-05-08 16:52:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1671258,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9251730/v1_covered_ca1646ce-a22f-46fa-b5c6-c1432b6d9409.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"YOLO-MAFD: A Collaborative Detection Framework for Automated Recognition of Bridge Steel Structural Components","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":"YOLOv8, bridge inspection, structural component detection, attention mechanism, multi-scale feature fusion","lastPublishedDoi":"10.21203/rs.3.rs-9251730/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9251730/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutomatic recognition of bridge steel structural components is crucial for intelligent bridge inspection and structural assessment. This study addresses a four-class detection task involving bearings, out-of-plane stiffeners (OPS), gusset plate connections (GPC), and cover plate terminations (CPT) in complex bridge scenes. Although YOLOv8 provides an efficient detection framework, its performance is limited by insufficient discriminative feature extraction, information loss during multi-scale fusion, and instability in classification and localization under background interference and class similarity. To address these limitations, a collaborative detection architecture, termed YOLO-MAFD, is proposed by introducing an attention-enhanced convolution module into the backbone, an optimized multi-scale feature fusion strategy into the neck, and an improved decoupled prediction head. Experimental results show that the proposed method outperforms the baseline YOLOv8 model, achieving an [email protected] of 0.766, corresponding to a 9.4% relative improvement, while also improving [email protected]:0.95 and Recall. These results demonstrate that the proposed method improves the accuracy and robustness of bridge steel structural component detection, particularly under complex backgrounds and multi-class interference.\u003c/p\u003e","manuscriptTitle":"YOLO-MAFD: A Collaborative Detection Framework for Automated Recognition of Bridge Steel Structural Components","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-06 12:14:22","doi":"10.21203/rs.3.rs-9251730/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":"c7545f74-7637-4559-9f1a-4d996a14c5d6","owner":[],"postedDate":"April 6th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-08T15:43:53+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-08T01:21:32+00:00","index":31,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-07T11:22:30+00:00","index":30,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-08T16:41:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-06 12:14:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9251730","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9251730","identity":"rs-9251730","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}