Underwater Image Object Detection based on Multi-scale Feature Fusion

Underwater Image Object Detection based on Multi-scale Feature Fusion | 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 Underwater Image Object Detection based on Multi-scale Feature Fusion Chao Yang, Ce Zhang, Longyu Jiang, Xinwen Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4114831/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Sep, 2024 Read the published version in Machine Vision and Applications → Version 1 posted 9 You are reading this latest preprint version Abstract Underwater object detection and classification technology is one of the most important ways for humans to explore the oceans. However, existing methods are still insufficient in terms of accuracy and speed, and have poor detection performance for small objects such as fish. In this paper, we propose a multi-scale aggregation enhanced (MAE-FPN) object detection method based on the feature pyramid network, including the multi-scale convolutional calibration module (MCCM) and the feature calibration distribution module (FCDM). First, we design the MCCM module, which can adaptively extract feature information from objects at different scales. Then, we built the FCDM structure to make the multi-scale information fusion more appropriate and to alleviate the problem of missing features from small objects. Finally, we construct the Fish Segmentation and Detection (FSD) dataset by fusing multiple data augmentation methods, which enriches the data resources for underwater object detection and solves the problem of limited training resources for deep learning. We conduct experiments on FSD and public datasets, and the results show that the proposed MAE-FPN network significantly improves the detection performance of underwater objects, especially small objects. underwater image object detection deep learning feature fusion data augmentation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Sep, 2024 Read the published version in Machine Vision and Applications → Version 1 posted Editorial decision: Revision requested 03 Jul, 2024 Reviews received at journal 03 Jul, 2024 Reviewers agreed at journal 29 May, 2024 Reviews received at journal 01 May, 2024 Reviewers agreed at journal 25 Apr, 2024 Reviewers invited by journal 22 Apr, 2024 Editor assigned by journal 18 Mar, 2024 Submission checks completed at journal 18 Mar, 2024 First submitted to journal 16 Mar, 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-4114831","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":280682086,"identity":"18cee3d9-85c5-4f86-b1f3-c5de7ecd48a7","order_by":0,"name":"Chao Yang","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Chao","middleName":"","lastName":"Yang","suffix":""},{"id":280682087,"identity":"871d94ba-d4b6-4e8b-83fa-9b207ee92564","order_by":1,"name":"Ce Zhang","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ce","middleName":"","lastName":"Zhang","suffix":""},{"id":280682088,"identity":"2d0b9e8a-b49b-4a93-9487-3870be8a5b24","order_by":2,"name":"Longyu Jiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAoElEQVRIiWNgGAWjYBAC9hk8hg8gzAQitTDO4DE2IFULW5oEqVqYj1X+qDjMwM+eY8DwcwdRWhjbbvOcOcwg2fPGgLH3DLFaGNsOMxjcyDFgZmwjUkvhz3+HGeyJ1iII1MLA2wC0RYJYLdISjM3SPMfSeSTOPCs42EuMFj75g40ff9RYy/G3J2988JMYLTDAAyIOkKBhFIyCUTAKRgE+AAAISDE0f+B+7wAAAABJRU5ErkJggg==","orcid":"","institution":"Southeast University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Longyu","middleName":"","lastName":"Jiang","suffix":""},{"id":280682089,"identity":"27ea8881-7b47-4191-ac53-62b3ebd1531e","order_by":3,"name":"Xinwen Zhang","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xinwen","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-03-16 22:44:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4114831/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4114831/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00138-024-01606-3","type":"published","date":"2024-09-02T16:05:11+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":64185729,"identity":"5834b1e2-3c32-494c-b16e-7339938d146d","added_by":"auto","created_at":"2024-09-09 16:21:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1910518,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4114831/v1_covered_0dd02f24-1189-4359-9ff2-7bb9e1e8d2df.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Underwater Image Object Detection based on Multi-scale Feature Fusion","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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"underwater image object detection, deep learning, feature fusion, data augmentation","lastPublishedDoi":"10.21203/rs.3.rs-4114831/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4114831/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Underwater object detection and classification technology is one of the most important ways for humans to explore the oceans. However, existing methods are still insufficient in terms of accuracy and speed, and have poor detection performance for small objects such as fish. In this paper, we propose a multi-scale aggregation enhanced (MAE-FPN) object detection method based on the feature pyramid network, including the multi-scale convolutional calibration module (MCCM) and the feature calibration distribution module (FCDM). First, we design the MCCM module, which can adaptively extract feature information from objects at different scales. Then, we built the FCDM structure to make the multi-scale information fusion more appropriate and to alleviate the problem of missing features from small objects. Finally, we construct the Fish Segmentation and Detection (FSD) dataset by fusing multiple data augmentation methods, which enriches the data resources for underwater object detection and solves the problem of limited training resources for deep learning. We conduct experiments on FSD and public datasets, and the results show that the proposed MAE-FPN network significantly improves the detection performance of underwater objects, especially small objects.","manuscriptTitle":"Underwater Image Object Detection based on Multi-scale Feature Fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-20 18:47:15","doi":"10.21203/rs.3.rs-4114831/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-07-04T03:03:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-07-04T03:02:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"294213013262284919313428119048460319518","date":"2024-05-29T15:25:00+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-01T05:51:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7c470fe1-3a35-4d95-8d00-325689ce9a3d","date":"2024-04-26T00:52:07+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-22T08:10:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-03-18T04:15:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-18T04:15:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2024-03-16T22:42:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"0634800c-bbbd-4c7b-bc56-d2216a9ed01b","owner":[],"postedDate":"March 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-09-09T16:11:01+00:00","versionOfRecord":{"articleIdentity":"rs-4114831","link":"https://doi.org/10.1007/s00138-024-01606-3","journal":{"identity":"machine-vision-and-applications","isVorOnly":false,"title":"Machine Vision and Applications"},"publishedOn":"2024-09-02 16:05:11","publishedOnDateReadable":"September 2nd, 2024"},"versionCreatedAt":"2024-03-20 18:47:15","video":"","vorDoi":"10.1007/s00138-024-01606-3","vorDoiUrl":"https://doi.org/10.1007/s00138-024-01606-3","workflowStages":[]},"version":"v1","identity":"rs-4114831","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4114831","identity":"rs-4114831","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}