Crack-SAM: Crack Segmentation Using a Foundation Model

Crack-SAM: Crack Segmentation Using a Foundation Model | 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 Crack-SAM: Crack Segmentation Using a Foundation Model Rakshitha R, Srinath S, N Vinay Kumar, Rashmi S, Poornima B V This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4780874/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Oct, 2024 Read the published version in Journal of Infrastructure Preservation and Resilience → Version 1 posted 11 You are reading this latest preprint version Abstract Ensuring the structural integrity of pavements requires precise crack detection and evaluation. Manual inspections, although essential, are labour-intensive, time-consuming, and susceptible to errors, emphasizing the need for automated visual inspection techniques. This study presents an integrated approach to crack assessment by utilizing advanced visual models such as the Detectron2 model zoo and the Segment Anything Model (SAM) on Dataset A and Dataset B, which contain images from diverse locations with complex backgrounds and varying crack structures. Experiments were conducted using the Detectron2 model with four baseline configurations (mask_rcnn_R_50_FPN_3x, mask_rcnn_R_101_FPN_3x, fast_rcnn_R_50_FPN_3x, and fast_rcnn_R_101_FPN_3x), selected for their proven performance in object detection tasks and their ability to balance computational efficiency with high detection accuracy. Additionally, SAM was fine-tuned with three loss functions (Focal Loss, DiceCELoss, and DiceFocalLoss) chosen for their effectiveness in handling class imbalance and improving segmentation accuracy. Results demonstrate that SAM fine-tuned with DiceFocalLoss outperforms Detectron2 in crack segmentation, achieving mean intersection over union (MIoU) values of 0.69 for Dataset A and 0.59 for Dataset B. The integration of Detectron2 with fast_rcnn_R_101_FPN_3x as the baseline and SAM with DiceFocalLoss involves training the Detectron2 model to generate approximate bounding boxes around objects of interest, which are then used as prompts for the SAM model to produce segmentation masks, resulting in MIoU values of 0.83 for Dataset A and 0.75 for Dataset B. These findings represent significant advancements in crack identification methods, with substantial implications for improving highway maintenance practices. Crack detection Crack segmentation SAM model Detectron2 model Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Oct, 2024 Read the published version in Journal of Infrastructure Preservation and Resilience → Version 1 posted Editorial decision: Revision requested 05 Aug, 2024 Reviews received at journal 04 Aug, 2024 Reviews received at journal 03 Aug, 2024 Reviews received at journal 01 Aug, 2024 Reviewers agreed at journal 25 Jul, 2024 Reviewers agreed at journal 24 Jul, 2024 Reviewers agreed at journal 24 Jul, 2024 Reviewers invited by journal 24 Jul, 2024 Editor assigned by journal 24 Jul, 2024 Submission checks completed at journal 24 Jul, 2024 First submitted to journal 22 Jul, 2024 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-4780874","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":336002618,"identity":"90e13465-a329-41da-b71e-7a7b217d3eca","order_by":0,"name":"Rakshitha R","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIie3RsWoCQRCA4TkW1maD7YghzzBwkNj5KrcIl8YcBzZWciCcjQ9gFV9B32DlQBsfwNLKNCkOrr0is2fAaj3LQPavlmU+mGUBfL4/mQQBBBGfgjP+3hkAdIsrIUsE2Tn1GIGGyGZMta31ttiPqjStk272dJkO6tlwiB+7QsEgcZHnY7zvr4gmaDqvp15e6CUmEROcuAjCey4Ukc6MlKdeZiKFY9qtAHXmIt2veWXJmkmKvFg7wdj0LdkwAZQiWDIx5V1yiZmEeltIgc1bjt9M6N5icVip+kV/HvKgsot1FuOwjKYzJ7nFvyNu/0et89eC8sFBn8/n+1/9AHdfTmb94Y9LAAAAAElFTkSuQmCC","orcid":"","institution":"JSS Science and Technology University","correspondingAuthor":true,"prefix":"","firstName":"Rakshitha","middleName":"","lastName":"R","suffix":""},{"id":336002624,"identity":"edafd89c-02c3-401d-94d1-b30ec2473795","order_by":1,"name":"Srinath S","email":"","orcid":"","institution":"JSS Science and Technology University","correspondingAuthor":false,"prefix":"","firstName":"Srinath","middleName":"","lastName":"S","suffix":""},{"id":336002625,"identity":"f295557b-7927-43d7-a3dc-0a6d3c995227","order_by":2,"name":"N Vinay Kumar","email":"","orcid":"","institution":"Freelance Researcher","correspondingAuthor":false,"prefix":"","firstName":"N","middleName":"Vinay","lastName":"Kumar","suffix":""},{"id":336002627,"identity":"31d5d852-61d6-4dae-b048-f57eba0c8357","order_by":3,"name":"Rashmi S","email":"","orcid":"","institution":"JSS Science and Technology University","correspondingAuthor":false,"prefix":"","firstName":"Rashmi","middleName":"","lastName":"S","suffix":""},{"id":336002628,"identity":"d26e03d9-f264-472d-a82b-8e362244be15","order_by":4,"name":"Poornima B V","email":"","orcid":"","institution":"JSS Science and Technology University","correspondingAuthor":false,"prefix":"","firstName":"Poornima","middleName":"B","lastName":"V","suffix":""}],"badges":[],"createdAt":"2024-07-22 09:54:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4780874/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4780874/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s43065-024-00103-1","type":"published","date":"2024-10-02T15:58:16+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":66097005,"identity":"7414e06b-eed8-43eb-9512-a68d3b12ecd0","added_by":"auto","created_at":"2024-10-07 16:12:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":757925,"visible":true,"origin":"","legend":"","description":"","filename":"FinalSAMpaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4780874/v1_covered_76d9fa3d-f053-4851-ae05-1109388ab1e9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Crack-SAM: Crack Segmentation Using a Foundation Model","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":"journal-of-infrastructure-preservation-and-resilience","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jipr","sideBox":"Learn more about [Journal of Infrastructure Preservation and Resilience](https://jipr.springeropen.com)","snPcode":"43065","submissionUrl":"https://submission.nature.com/new-submission/43065/3","title":"Journal of Infrastructure Preservation and Resilience","twitterHandle":"@SpringerEng","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Crack detection, Crack segmentation, SAM model, Detectron2 model","lastPublishedDoi":"10.21203/rs.3.rs-4780874/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4780874/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEnsuring the structural integrity of pavements requires precise crack detection and evaluation. Manual inspections, although essential, are labour-intensive, time-consuming, and susceptible to errors, emphasizing the need for automated visual inspection techniques. This study presents an integrated approach to crack assessment by utilizing advanced visual models such as the Detectron2 model zoo and the Segment Anything Model (SAM) on Dataset A and Dataset B, which contain images from diverse locations with complex backgrounds and varying crack structures. Experiments were conducted using the Detectron2 model with four baseline configurations (mask_rcnn_R_50_FPN_3x, mask_rcnn_R_101_FPN_3x, fast_rcnn_R_50_FPN_3x, and fast_rcnn_R_101_FPN_3x), selected for their proven performance in object detection tasks and their ability to balance computational efficiency with high detection accuracy. Additionally, SAM was fine-tuned with three loss functions (Focal Loss, DiceCELoss, and DiceFocalLoss) chosen for their effectiveness in handling class imbalance and improving segmentation accuracy. Results demonstrate that SAM fine-tuned with DiceFocalLoss outperforms Detectron2 in crack segmentation, achieving mean intersection over union (MIoU) values of 0.69 for Dataset A and 0.59 for Dataset B. The integration of Detectron2 with fast_rcnn_R_101_FPN_3x as the baseline and SAM with DiceFocalLoss involves training the Detectron2 model to generate approximate bounding boxes around objects of interest, which are then used as prompts for the SAM model to produce segmentation masks, resulting in MIoU values of 0.83 for Dataset A and 0.75 for Dataset B. These findings represent significant advancements in crack identification methods, with substantial implications for improving highway maintenance practices.\u003c/p\u003e","manuscriptTitle":"Crack-SAM: Crack Segmentation Using a Foundation Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-21 04:26:21","doi":"10.21203/rs.3.rs-4780874/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-05T08:07:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-04T16:53:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-03T06:50:02+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-01T15:51:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60990885414776777980010475670976780047","date":"2024-07-25T16:43:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"76237444500385017347045385372413564165","date":"2024-07-25T01:27:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"35012288146832664580985809248869875718","date":"2024-07-25T01:20:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-25T01:18:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-25T00:15:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-24T19:46:01+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Infrastructure Preservation and Resilience","date":"2024-07-22T09:53:16+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-infrastructure-preservation-and-resilience","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jipr","sideBox":"Learn more about [Journal of Infrastructure Preservation and Resilience](https://jipr.springeropen.com)","snPcode":"43065","submissionUrl":"https://submission.nature.com/new-submission/43065/3","title":"Journal of Infrastructure Preservation and Resilience","twitterHandle":"@SpringerEng","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a84aa6ea-8c85-4d25-90e8-293a48fb2a9a","owner":[],"postedDate":"August 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-10-07T16:05:12+00:00","versionOfRecord":{"articleIdentity":"rs-4780874","link":"https://doi.org/10.1186/s43065-024-00103-1","journal":{"identity":"journal-of-infrastructure-preservation-and-resilience","isVorOnly":false,"title":"Journal of Infrastructure Preservation and Resilience"},"publishedOn":"2024-10-02 15:58:16","publishedOnDateReadable":"October 2nd, 2024"},"versionCreatedAt":"2024-08-21 04:26:21","video":"","vorDoi":"10.1186/s43065-024-00103-1","vorDoiUrl":"https://doi.org/10.1186/s43065-024-00103-1","workflowStages":[]},"version":"v1","identity":"rs-4780874","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4780874","identity":"rs-4780874","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}