D2Net: a dual-branch lightweight network for conveyor belt rotation detection in pipe belt conveyors

D2Net: a dual-branch lightweight network for conveyor belt rotation detection in pipe belt conveyors | 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 D2Net: a dual-branch lightweight network for conveyor belt rotation detection in pipe belt conveyors Xingyu Wang, Nini Hao, Yu Yun, Mengchao Zhang, Yuan Zhang, Zeqing Zhong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5417187/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Jan, 2025 Read the published version in Journal of Real-Time Image Processing → Version 1 posted 10 You are reading this latest preprint version Abstract Due to the swift advancement of artificial intelligence technology, semantic segmentation has emerged as a critical method for identifying rotational flaws in conveyor belts of pipe belt conveyors. Nonetheless, current segmentation algorithm models typically exhibit issues of excessive model parameters and sluggish inference speed, making it challenging to simultaneously satisfy the accuracy demands of conveyor belt edge segmentation and real-time requirements, thereby complicating their adaptation to the real-time monitoring needs of actual production lines. This research offers an efficient backbone network, D2Net, for real-time semantic segmentation of conveyor belt edges to address this issue. The network comprises a dual-branch Deep Dual-Resolution Network that facilitates information exchange across the branches via several bilateral fusion processes. A Multi-Scale Attention Aggregation Module (MSAAM) is developed to effectively broaden the network's sensory field and improve segmentation performance via multi-scale contextual fusion of low-resolution feature maps. This research constructs a dataset of pipe belt conveyor operations at a steel factory across three locations to validate the model's performance, and the suggested network is trained and tested using this dataset. The experimental findings indicate that the network attains an average intersection over union (mIoU) of 75.34% on a dataset with a resolution of 512 × 512, while the inference speed reaches 169.5 frames per second (fps), and the model comprises merely 22.9 MB of parameters. This research demonstrates that the D2Net achieves an effective equilibrium between speed and accuracy in the belt edge segmentation of rpipe belt conveyors. It exhibits optimal equilibrium and delivers robust technical assistance for real-time semantic segmentation in edge computing environments. Semantic segmentation Pipe belt conveyor Conveyor belt rotation detection Lightweight network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Jan, 2025 Read the published version in Journal of Real-Time Image Processing → Version 1 posted Editorial decision: Revision requested 02 Dec, 2024 Reviews received at journal 01 Dec, 2024 Reviewers agreed at journal 24 Nov, 2024 Reviews received at journal 19 Nov, 2024 Reviewers agreed at journal 12 Nov, 2024 Reviewers agreed at journal 12 Nov, 2024 Reviewers invited by journal 09 Nov, 2024 Editor assigned by journal 09 Nov, 2024 Submission checks completed at journal 09 Nov, 2024 First submitted to journal 08 Nov, 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-5417187","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":381873965,"identity":"ceff38b2-2062-40e5-9358-a11705382b22","order_by":0,"name":"Xingyu Wang","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xingyu","middleName":"","lastName":"Wang","suffix":""},{"id":381873966,"identity":"c96ef9db-fd2f-4fe1-a92a-1f2f215d1fb2","order_by":1,"name":"Nini Hao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIiWNgGAWjYDACHgbDBx8MbHj42RsYJCBCCQS1GBvOKEiTkew5ANJiQJQWM2meD4dtDG4kEKlFvufwNmkegzQehpvPH97m+fOHgZ89x4Dh5w7cWgzOthVbzgH6hXF2jrE1b5sBg2TPGwPG3jN4tPDzGN54A7SFWTqHTZq3wYDB4EaOATNjGx6H9fMYSPAYHOZhkzz+TJrnjwGDPSEtDGd7jCRBWngkQOHABrRFgoAWgzPHig1nAB0mwZNjbDm3zZhH4syzgoO9+BzWk7zxwYc/Nvb2x48/vPHmj5wcfztQ5Cc+h6EDHhBxgAQNo2AUjIJRMAqwAAAOAkuwfF3hWgAAAABJRU5ErkJggg==","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Nini","middleName":"","lastName":"Hao","suffix":""},{"id":381873967,"identity":"137a2267-3a90-4ed5-9dc0-d59d44c6e92b","order_by":2,"name":"Yu Yun","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Yun","suffix":""},{"id":381873968,"identity":"db9de57b-f28d-403c-87cb-42f932fec5e2","order_by":3,"name":"Mengchao Zhang","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Mengchao","middleName":"","lastName":"Zhang","suffix":""},{"id":381873969,"identity":"c45a64aa-5557-4213-8cea-bb074c1ad288","order_by":4,"name":"Yuan Zhang","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yuan","middleName":"","lastName":"Zhang","suffix":""},{"id":381873970,"identity":"3ba9b43f-0afc-4699-bf80-8610e093da47","order_by":5,"name":"Zeqing Zhong","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zeqing","middleName":"","lastName":"Zhong","suffix":""}],"badges":[],"createdAt":"2024-11-08 14:23:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5417187/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5417187/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11554-024-01614-6","type":"published","date":"2025-01-03T15:56:59+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":73093284,"identity":"b8f1459e-ab37-4834-9fb9-e2325fd896c3","added_by":"auto","created_at":"2025-01-06 16:12:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3904118,"visible":true,"origin":"","legend":"","description":"","filename":"Wang5a26bd48.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5417187/v1_covered_946e383b-8a2e-4cc9-9a48-76ac0d3f3c5c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"D2Net: a dual-branch lightweight network for conveyor belt rotation detection in pipe belt conveyors","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-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Semantic segmentation, Pipe belt conveyor, Conveyor belt rotation detection, Lightweight network","lastPublishedDoi":"10.21203/rs.3.rs-5417187/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5417187/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Due to the swift advancement of artificial intelligence technology, semantic segmentation has emerged as a critical method for identifying rotational flaws in conveyor belts of pipe belt conveyors. Nonetheless, current segmentation algorithm models typically exhibit issues of excessive model parameters and sluggish inference speed, making it challenging to simultaneously satisfy the accuracy demands of conveyor belt edge segmentation and real-time requirements, thereby complicating their adaptation to the real-time monitoring needs of actual production lines. This research offers an efficient backbone network, D2Net, for real-time semantic segmentation of conveyor belt edges to address this issue. The network comprises a dual-branch Deep Dual-Resolution Network that facilitates information exchange across the branches via several bilateral fusion processes. A Multi-Scale Attention Aggregation Module (MSAAM) is developed to effectively broaden the network's sensory field and improve segmentation performance via multi-scale contextual fusion of low-resolution feature maps. This research constructs a dataset of pipe belt conveyor operations at a steel factory across three locations to validate the model's performance, and the suggested network is trained and tested using this dataset. The experimental findings indicate that the network attains an average intersection over union (mIoU) of 75.34% on a dataset with a resolution of 512 × 512, while the inference speed reaches 169.5 frames per second (fps), and the model comprises merely 22.9 MB of parameters. This research demonstrates that the D2Net achieves an effective equilibrium between speed and accuracy in the belt edge segmentation of rpipe belt conveyors. It exhibits optimal equilibrium and delivers robust technical assistance for real-time semantic segmentation in edge computing environments.","manuscriptTitle":"D2Net: a dual-branch lightweight network for conveyor belt rotation detection in pipe belt conveyors","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-27 07:41:30","doi":"10.21203/rs.3.rs-5417187/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-02T14:58:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-02T04:33:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"252992481686486034868730794372055835035","date":"2024-11-24T09:08:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-19T15:07:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"294304836604295428717512723902942573718","date":"2024-11-12T13:38:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"94071053396116362022179039303491211121","date":"2024-11-12T08:46:43+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-09T17:42:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-09T09:26:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-09T09:26:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Real-Time Image Processing","date":"2024-11-08T14:07:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e3f1f863-6518-41e5-be00-f1b97ef09bda","owner":[],"postedDate":"November 27th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-01-06T16:02:10+00:00","versionOfRecord":{"articleIdentity":"rs-5417187","link":"https://doi.org/10.1007/s11554-024-01614-6","journal":{"identity":"journal-of-real-time-image-processing","isVorOnly":false,"title":"Journal of Real-Time Image Processing"},"publishedOn":"2025-01-03 15:56:59","publishedOnDateReadable":"January 3rd, 2025"},"versionCreatedAt":"2024-11-27 07:41:30","video":"","vorDoi":"10.1007/s11554-024-01614-6","vorDoiUrl":"https://doi.org/10.1007/s11554-024-01614-6","workflowStages":[]},"version":"v1","identity":"rs-5417187","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5417187","identity":"rs-5417187","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}