GSB-YOLO: An Enhanced Lightweight Model for Robust Road Crack Detection with Multi-Scale Feature Fusion in Complex Environments

GSB-YOLO: An Enhanced Lightweight Model for Robust Road Crack Detection with Multi-Scale Feature Fusion in Complex Environments | 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 GSB-YOLO: An Enhanced Lightweight Model for Robust Road Crack Detection with Multi-Scale Feature Fusion in Complex Environments Yuhao Wang, Jianping Liu, Jun Xie, Jiong Mu, Qianqian Wu, Xiuyuan Lu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6119624/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract Timely detection and regular maintenance of road cracks are critical for road and traffic safety. However, existing detection methods face challenges such as varying target scales, large model parameters, and poor adaptability to complex backgrounds. To address these issues, this study proposes an enhanced GSB-YOLO model. Inspired by the concepts of linear transformation and long-range attention mechanisms, a lightweight network structure was designed to reduce model parameters in the backbone network, thereby improving detection efficiency. Additionally, a novel SMC2f module was introduced in the neck structure, which calculates the "energy" of each neuron in the feature map, evaluates its contribution to the detection task, and dynamically assigns weighted coefficients. This method enhances the model's detection robustness in complex backgrounds and effectively addresses the issue of insufficient emphasis on positive samples. Furthermore, through the optimization of the Path Aggregation Network (PAN) and the Bidirectional Feature Pyramid Network (BiFPN), efficient multi-scale feature fusion is achieved, further strengthening the model's capacity to represent crack features at various scales. Experimental results indicate that the proposed GSB-YOLO model improves the mean average precision (mAP) in road crack detection tasks by 3.2%, demonstrating its significant application value in road crack detection and traffic safety assurance. Biological sciences/Computational biology and bioinformatics Earth and environmental sciences/Environmental sciences Physical sciences/Mathematics and computing Road crack detection GSB-YOLO SMC2f module multi-scale feature fusion YOLOv8n Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 06 May, 2025 Reviews received at journal 26 Apr, 2025 Reviews received at journal 18 Apr, 2025 Reviewers agreed at journal 18 Apr, 2025 Reviewers agreed at journal 17 Apr, 2025 Reviewers invited by journal 15 Apr, 2025 Submission checks completed at journal 15 Apr, 2025 First submitted to journal 15 Apr, 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-6119624","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":443258189,"identity":"c18b6731-d677-428d-9090-d65c43f16e0c","order_by":0,"name":"Yuhao Wang","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Yuhao","middleName":"","lastName":"Wang","suffix":""},{"id":443258191,"identity":"3bf1ef11-80b9-4404-9c0e-ed52765798b5","order_by":1,"name":"Jianping Liu","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Jianping","middleName":"","lastName":"Liu","suffix":""},{"id":443258192,"identity":"5d6ed36a-41ff-4914-bc5c-bafabf979301","order_by":2,"name":"Jun Xie","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Xie","suffix":""},{"id":443258193,"identity":"40f66915-b520-43ef-bb5d-c6524a27369e","order_by":3,"name":"Jiong Mu","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Jiong","middleName":"","lastName":"Mu","suffix":""},{"id":443258194,"identity":"2d901c53-7b7f-4c3b-b742-e47aac816e12","order_by":4,"name":"Qianqian Wu","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Qianqian","middleName":"","lastName":"Wu","suffix":""},{"id":443258195,"identity":"51521612-5563-4d08-a486-532edcc424f7","order_by":5,"name":"Xiuyuan Lu","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Xiuyuan","middleName":"","lastName":"Lu","suffix":""},{"id":443258196,"identity":"4a469885-3278-47a7-a3f7-a823c9af9c3c","order_by":6,"name":"Yirong Wang","email":"","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Yirong","middleName":"","lastName":"Wang","suffix":""},{"id":443258197,"identity":"0122cf03-e164-424a-9ae2-4634ea528ebb","order_by":7,"name":"Siyue Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIie3RMUvEMBTA8Ujg3fKwa46T9itEChWpnl+lIXC3iSBIxh6F3OgX8EN0dUsI6FKcD26puDp4i7hp2lVbOjrkPz7y4wUeIaHQPwwSW5qCXyBQaltFaD9lY+SY0Y1p1SqOZiB5M4XEbFbZtnHp/B4zNonAYlMaoamoHayU1XlyRqjdI1leD5IT2xHwhD7trF6fPpYgcyTydpAQ0RHst+wP2h3VBrMFEiPKccI8wezGandVm+hznDBPioan8woz4onwW2CcYHcXVcQRBcnMy1r6H6bnD1wOkmS7fTt88W+EyNkPc5df1s/V6+5dLQfJH/Wn4dPfh0KhUOh3PwjRYBcZ+1gEAAAAAElFTkSuQmCC","orcid":"","institution":"Sichuan Agricultural University","correspondingAuthor":true,"prefix":"","firstName":"Siyue","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2025-02-27 09:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6119624/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6119624/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-11717-0","type":"published","date":"2025-07-22T15:56:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":87756579,"identity":"3c19c478-9f72-45da-adf8-db6d4c31cf85","added_by":"auto","created_at":"2025-07-28 16:04:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":986558,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6119624/v1_covered_cdc1d08f-e91e-4bde-ae98-908223962dee.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GSB-YOLO: An Enhanced Lightweight Model for Robust Road Crack Detection with Multi-Scale Feature Fusion in Complex Environments","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":"Road crack detection, GSB-YOLO, SMC2f module, multi-scale feature fusion, YOLOv8n","lastPublishedDoi":"10.21203/rs.3.rs-6119624/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6119624/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTimely detection and regular maintenance of road cracks are critical for road and traffic safety. However, existing detection methods face challenges such as varying target scales, large model parameters, and poor adaptability to complex backgrounds. To address these issues, this study proposes an enhanced GSB-YOLO model. Inspired by the concepts of linear transformation and long-range attention mechanisms, a lightweight network structure was designed to reduce model parameters in the backbone network, thereby improving detection efficiency. Additionally, a novel SMC2f module was introduced in the neck structure, which calculates the \"energy\" of each neuron in the feature map, evaluates its contribution to the detection task, and dynamically assigns weighted coefficients. This method enhances the model's detection robustness in complex backgrounds and effectively addresses the issue of insufficient emphasis on positive samples. Furthermore, through the optimization of the Path Aggregation Network (PAN) and the Bidirectional Feature Pyramid Network (BiFPN), efficient multi-scale feature fusion is achieved, further strengthening the model's capacity to represent crack features at various scales. Experimental results indicate that the proposed GSB-YOLO model improves the mean average precision (mAP) in road crack detection tasks by 3.2%, demonstrating its significant application value in road crack detection and traffic safety assurance.\u003c/p\u003e","manuscriptTitle":"GSB-YOLO: An Enhanced Lightweight Model for Robust Road Crack Detection with Multi-Scale Feature Fusion in Complex Environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-16 06:21:40","doi":"10.21203/rs.3.rs-6119624/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-06T09:40:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-26T04:19:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-18T08:46:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"14759833354685340462821513462433033297","date":"2025-04-18T08:26:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247807633579954563487148517443663177104","date":"2025-04-17T14:03:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-15T12:02:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-15T08:58:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-15T05:27:32+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":"bcfe4dea-c5f8-412e-824b-92eb8b1ffaa7","owner":[],"postedDate":"April 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":47192145,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":47192146,"name":"Earth and environmental sciences/Environmental sciences"},{"id":47192147,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-07-28T15:58:55+00:00","versionOfRecord":{"articleIdentity":"rs-6119624","link":"https://doi.org/10.1038/s41598-025-11717-0","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-07-22 15:56:52","publishedOnDateReadable":"July 22nd, 2025"},"versionCreatedAt":"2025-04-16 06:21:40","video":"","vorDoi":"10.1038/s41598-025-11717-0","vorDoiUrl":"https://doi.org/10.1038/s41598-025-11717-0","workflowStages":[]},"version":"v1","identity":"rs-6119624","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6119624","identity":"rs-6119624","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}