EdgeFlowNet: A Lightweight, Dynamic Edge-Aware Network for Precise Water Surface Boundary Detection

EdgeFlowNet: A Lightweight, Dynamic Edge-Aware Network for Precise Water Surface Boundary Detection | 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 EdgeFlowNet: A Lightweight, Dynamic Edge-Aware Network for Precise Water Surface Boundary Detection Xiao-ting Guo, Yu-xuan Liao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7105148/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Water surface edge detection demands lightweight solutions for real-time marine navigation, maintaining high precision under diverse environmental conditions. This paper introduces EdgeFlowNet, a lightweight and environment-robust edge-aware network designed specifically for water surface boundary detection. EdgeFlowNet integrates a Dynamic Importance Weighting (DIW) module for adaptive fusion of edge and semantic features, a hybrid dual-branch architecture combining classical edge operators with deep learning, and binary classification optimization for extreme parameter efficiency. Evaluated on the WaterScenes dataset across 192 environmental conditions, EdgeFlowNet-Efficient (74K parameters) achieves 97.83% mIoU at 76.8 FPS, outperforming PiDiNet by 0.67% mIoU with 52.6% fewer parameters and 82% faster processing. Our approach demonstrates strong robustness and an improved accuracy-efficiency trade-off, facilitating deployment in resource-constrained autonomous marine systems. The source code of our EdgeFlowNet model is available at https://github.com/Wuuu10/EdgeFlowNet . Edge detection Lightweight networks Water surface segmentation Dynamic feature fusion Attention mechanisms Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Dec, 2025 Reviews received at journal 25 Dec, 2025 Reviewers agreed at journal 20 Dec, 2025 Reviews received at journal 18 Dec, 2025 Reviewers agreed at journal 17 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers invited by journal 21 Jul, 2025 Editor assigned by journal 13 Jul, 2025 Submission checks completed at journal 12 Jul, 2025 First submitted to journal 11 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-7105148","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":488853061,"identity":"eaf06302-92fc-4e19-b60d-0c71ca7d5006","order_by":0,"name":"Xiao-ting Guo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYLCCBCBmY2BgfIDgEqFFAqiF2YB4LUAgAbJIgigt8hHJxyQe1NjU8Um3X6subLNj4GfPMWD4uQO3FsMbackGCcfSJNhkzpTdntmWzCDZ88aAsfcMHi0zcgwfJLAdlmCTyEm7zdt2gMHgRo4BM2MbXi0GBxL+QbQUg7TYE9IiLwG0JbENpCX9GDPYFgkCWgx4niUbJPalSbZJ5DBL85xL5pE486zgYC8+W9qTj0n++GbDLz8j/eFnnjI7Of725I0PfuKz5QCcyQOOSR4QcQCrWpgtDXAm+wN8CkfBKBgFo2AEAwB3dEn7YeTqEQAAAABJRU5ErkJggg==","orcid":"","institution":"North University of China","correspondingAuthor":true,"prefix":"","firstName":"Xiao-ting","middleName":"","lastName":"Guo","suffix":""},{"id":488853062,"identity":"2f1e11ac-dd68-4763-b1e0-7f50de6173ff","order_by":1,"name":"Yu-xuan Liao","email":"","orcid":"","institution":"North University of China","correspondingAuthor":false,"prefix":"","firstName":"Yu-xuan","middleName":"","lastName":"Liao","suffix":""}],"badges":[],"createdAt":"2025-07-12 02:08:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7105148/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7105148/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88505117,"identity":"d1f72f51-55b6-4ce2-8fb3-691c84b90275","added_by":"auto","created_at":"2025-08-07 07:17:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1026098,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7105148/v1_covered_bc814e4d-285e-447b-a836-804733539356.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EdgeFlowNet: A Lightweight, Dynamic Edge-Aware Network for Precise Water Surface Boundary Detection","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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Edge detection, Lightweight networks, Water surface segmentation, Dynamic feature fusion, Attention mechanisms","lastPublishedDoi":"10.21203/rs.3.rs-7105148/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7105148/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWater surface edge detection demands lightweight solutions for real-time marine navigation, maintaining high precision under diverse environmental conditions. This paper introduces EdgeFlowNet, a lightweight and environment-robust edge-aware network designed specifically for water surface boundary detection. EdgeFlowNet integrates a Dynamic Importance Weighting (DIW) module for adaptive fusion of edge and semantic features, a hybrid dual-branch architecture combining classical edge operators with deep learning, and binary classification optimization for extreme parameter efficiency. Evaluated on the WaterScenes dataset across 192 environmental conditions, EdgeFlowNet-Efficient (74K parameters) achieves 97.83% mIoU at 76.8 FPS, outperforming PiDiNet by 0.67% mIoU with 52.6% fewer parameters and 82% faster processing. Our approach demonstrates strong robustness and an improved accuracy-efficiency trade-off, facilitating deployment in resource-constrained autonomous marine systems. The source code of our EdgeFlowNet model is available at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/Wuuu10/EdgeFlowNet\u003c/span\u003e\u003cspan address=\"https://github.com/Wuuu10/EdgeFlowNet\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"EdgeFlowNet: A Lightweight, Dynamic Edge-Aware Network for Precise Water Surface Boundary Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-24 19:56:35","doi":"10.21203/rs.3.rs-7105148/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-27T06:52:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-25T13:55:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"105626874197984065076699452975984310487","date":"2025-12-21T02:19:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-18T07:24:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"246990778372637825358150584679647336117","date":"2025-12-18T03:13:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"306250742857982126077898896188893045455","date":"2025-12-16T03:28:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-22T01:25:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-13T11:41:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-12T10:20:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2025-07-12T02:03:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"4bb8597b-cbd7-4658-b7e1-49bc98884c92","owner":[],"postedDate":"July 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-20T16:11:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-24 19:56:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7105148","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7105148","identity":"rs-7105148","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}