PID-Former: A Triple Stream Network for Real-Time Coal Flow Segmentation

PID-Former: A Triple Stream Network for Real-Time Coal Flow Segmentation | 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 PID-Former: A Triple Stream Network for Real-Time Coal Flow Segmentation Zhi Xu, Xiaoming Zhang, Mei Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6607533/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Coal flow segmentation is the basis for detecting coal pile and coal flow deviation on conveyor belts, and the real-time performance and accuracy of segmentation methods are key factors affecting the above functions. However, segmenting coal flow from conveyor belts with similar color characteristics and complex lighting is a challenging task. To address the above issues, we proposed a triple stream semantic segmentation model PID-Former, which consists of P, I and D branches, and achieves real-time coal flow segmentation. Firstly, the I-Branch is designed for extracting context information based on lightweight transformer framework, and the P-Branch and D-Branch is constructed by the use of Inverted Residual Module (IRM) for detail and boundary information extracting respectively. Secondly, Context Information Fill Module (CIFM) and Edge Fusion Module (EFM) are proposed to combine different levels’ context information of I-Branch with P-Branch and D-Branch to supplement context information. At the same time, D-Branch strengthens the boundary information in features through the proposed Spatial Enhancement Block (SEB). Finally, the PID Fusion Block is designed to fuse the detail, context and boundary information extracted from P, I, D branches. Experimental results show that, PID-Former achieved the accuracy of 96.99% mIoU and 98.68% mPA on coal flow segmentation dataset, and reached a speed of 204.1FPS and 67.1FPS on the RTX3090 GPU and the embedded platform of NVIDIA Jetson TX2 respectively. Compared with the State-of-Arts, PID-Former achieved a better trade-off between accuracy and inference speed. Coal flow semantic segmentation Lightweight vision transformer Context information Feature fusion Full Text Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 29 May, 2025 Reviewers invited by journal 15 May, 2025 Editor assigned by journal 11 May, 2025 First submitted to journal 08 May, 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-6607533","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":456862142,"identity":"6dad278a-a68e-42a4-b162-d9964d3bfc06","order_by":0,"name":"Zhi Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIie3Pr4/CMBTA8TZNNlOC7QngX2gzieBfec2JmkGQCMRTRWK3P4OcOblkyTA9P7lTGMTQEH4lGMT1hkP0o95L3lc8QoLgDfUZK6Q+XYaPnf2ffKwszA/IkttMsVMinZOHHJnGzgmpQX31viOzzsyuIYuxxvin8BY0g8+k5/g0q1OFxBmNfAbehAmoEh6JKdYpRWpLjYJLbxIJvTrySJpRbX6RnjsknJdE5RZA3p5Cih0SEVsiW1eojdurDCqTWJ76k0nZbyUsitFwa5q2XY4H69j5k2dw/+6F+yAIguAPV6drSkPy8b7IAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-6241-2578","institution":"Anhui University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Zhi","middleName":"","lastName":"Xu","suffix":""},{"id":456862143,"identity":"d4eb2abc-1419-4b59-886e-d12aa4f6987e","order_by":1,"name":"Xiaoming Zhang","email":"","orcid":"","institution":"Anhui University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaoming","middleName":"","lastName":"Zhang","suffix":""},{"id":456862144,"identity":"bf800a2c-ac61-4f43-a39e-b0c8fa4ec976","order_by":2,"name":"Mei Zhang","email":"","orcid":"","institution":"Anhui University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Mei","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-05-07 03:19:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6607533/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6607533/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83042913,"identity":"3f79a29f-4e95-49d2-b599-eee069196192","added_by":"auto","created_at":"2025-05-19 11:06:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1044631,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6607533/v1_covered_b1b7f6e6-30e3-4dc2-83fd-5a4e73a2cdd4.pdf"}],"financialInterests":"","formattedTitle":"PID-Former: A Triple Stream Network for Real-Time Coal Flow Segmentation","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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Coal flow semantic segmentation, Lightweight vision transformer, Context information, Feature fusion","lastPublishedDoi":"10.21203/rs.3.rs-6607533/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6607533/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCoal flow segmentation is the basis for detecting coal pile and coal flow deviation on conveyor belts, and the real-time performance and accuracy of segmentation methods are key factors affecting the above functions. However, segmenting coal flow from conveyor belts with similar color characteristics and complex lighting is a challenging task. To address the above issues, we proposed a triple stream semantic segmentation model PID-Former, which consists of P, I and D branches, and achieves real-time coal flow segmentation. Firstly, the I-Branch is designed for extracting context information based on lightweight transformer framework, and the P-Branch and D-Branch is constructed by the use of Inverted Residual Module (IRM) for detail and boundary information extracting respectively. Secondly, Context Information Fill Module (CIFM) and Edge Fusion Module (EFM) are proposed to combine different levels\u0026rsquo; context information of I-Branch with P-Branch and D-Branch to supplement context information. At the same time, D-Branch strengthens the boundary information in features through the proposed Spatial Enhancement Block (SEB). Finally, the PID Fusion Block is designed to fuse the detail, context and boundary information extracted from P, I, D branches. Experimental results show that, PID-Former achieved the accuracy of 96.99% mIoU and 98.68% mPA on coal flow segmentation dataset, and reached a speed of 204.1FPS and 67.1FPS on the RTX3090 GPU and the embedded platform of NVIDIA Jetson TX2 respectively. Compared with the State-of-Arts, PID-Former achieved a better trade-off between accuracy and inference speed.\u003c/p\u003e","manuscriptTitle":"PID-Former: A Triple Stream Network for Real-Time Coal Flow Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-19 10:42:12","doi":"10.21203/rs.3.rs-6607533/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-05-29T11:29:41+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-15T05:50:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-11T20:28:26+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2025-05-08T10:35:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"720ee798-d29e-451c-b8b5-8c47c02bdc36","owner":[],"postedDate":"May 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-09-14T06:10:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-19 10:42:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6607533","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6607533","identity":"rs-6607533","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}