An Adaptive Crack Detection Network Based on Global-to-local Spatial Aggregation

An Adaptive Crack Detection Network Based on Global-to-local Spatial Aggregation | 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 An Adaptive Crack Detection Network Based on Global-to-local Spatial Aggregation Zhong Qu, Siyang Xu, Xuehui Yin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7131854/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Road cracks are a common form of damage in road maintenance. The complexity of crack shapes, textures, lighting conditions, and interference factors make accurate detection of cracks still a challenging task. To address these issues, we propose a novel adaptive crack detection network, which achieves precise crack recognition through an adaptive mechanism and multi-level feature fusion. The network is divided into multiple branches along the channel dimension, employing different convolution operations and assigning importance to dynamically select and emphasize key features. By utilizing cascaded large kernel convolution, the network captures rich multi-scale contextual information in deep layers. Additionally, the dual-stream design effectively integrates features from different hierarchical levels. We evaluated the proposed method on three benchmark crack detection datasets: DeepCrack, CFD, and Crack500. The method achieved F1 scores of 0.880, 0.669, and 0.746, and MIoU values of 0.887, 0.745, and 0.781, respectively, outperforming existing approaches. Crack detection Adaptive mechanism Cascaded large kernel convolution Dual-stream design Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 24 Jul, 2025 Reviewers invited by journal 24 Jul, 2025 Editor assigned by journal 17 Jul, 2025 Submission checks completed at journal 17 Jul, 2025 First submitted to journal 15 Jul, 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-7131854","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":490077278,"identity":"dac17a27-5d6b-44b5-917e-aaf28ac386fe","order_by":0,"name":"Zhong Qu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYHACNhAhB+MxNhCrxRjMPECKlsQGorXw3Uh/9uDjjtr0/vYcs8cfGGxkNxxgfvYAnxbJGwnphjPPHM+dceaNucEBhjTjDQfYzA3waTG4kXBMmrftWO4GiRwziQMMhxM3HOBhk8CvJbENpCXdAKLlPzFaktmAWmoSoFoOENYieeYZm+TMtgOGM848Kzc4Y5BsPPMwmxleLXzH059JfGyrk+dvT972oKLCTrbvePMzvFpAUQEEh4E4ARhBoKBixqserqUOqmUUjIJRMApGARYAAJrHTWybxwRzAAAAAElFTkSuQmCC","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Zhong","middleName":"","lastName":"Qu","suffix":""},{"id":490077279,"identity":"ba36836f-d7a4-4b6d-8564-141e44df57c1","order_by":1,"name":"Siyang Xu","email":"","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Siyang","middleName":"","lastName":"Xu","suffix":""},{"id":490077280,"identity":"6ff753d4-b1d7-42e9-9d7b-32f2a0579322","order_by":2,"name":"Xuehui Yin","email":"","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Xuehui","middleName":"","lastName":"Yin","suffix":""}],"badges":[],"createdAt":"2025-07-15 14:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7131854/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7131854/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87718240,"identity":"ca235319-f17f-4fc6-971a-4eb4fe7840fe","added_by":"auto","created_at":"2025-07-28 09:24:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1069402,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7131854/v1_covered_d44d70e4-87cd-4025-b55b-e0556d187de3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Adaptive Crack Detection Network Based on Global-to-local Spatial Aggregation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Crack detection, Adaptive mechanism, Cascaded large kernel convolution, Dual-stream design","lastPublishedDoi":"10.21203/rs.3.rs-7131854/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7131854/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRoad cracks are a common form of damage in road maintenance. The complexity of crack shapes, textures, lighting conditions, and interference factors make accurate detection of cracks still a challenging task. To address these issues, we propose a novel adaptive crack detection network, which achieves precise crack recognition through an adaptive mechanism and multi-level feature fusion. The network is divided into multiple branches along the channel dimension, employing different convolution operations and assigning importance to dynamically select and emphasize key features. By utilizing cascaded large kernel convolution, the network captures rich multi-scale contextual information in deep layers. Additionally, the dual-stream design effectively integrates features from different hierarchical levels. We evaluated the proposed method on three benchmark crack detection datasets: DeepCrack, CFD, and Crack500. The method achieved \u003cem\u003eF1\u003c/em\u003e scores of 0.880, 0.669, and 0.746, and \u003cem\u003eMIoU\u003c/em\u003e values of 0.887, 0.745, and 0.781, respectively, outperforming existing approaches.\u003c/p\u003e","manuscriptTitle":"An Adaptive Crack Detection Network Based on Global-to-local Spatial Aggregation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-28 09:00:05","doi":"10.21203/rs.3.rs-7131854/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-24T04:57:41+00:00","index":"","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-24T04:56:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-17T15:12:10+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-17T15:11:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2025-07-15T14:51:58+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d09bd443-6cff-4185-9edb-21b79871dbeb","owner":[],"postedDate":"July 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-07-28T09:00:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-28 09:00:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7131854","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7131854","identity":"rs-7131854","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}