Underwater Small Target Detection Based on Improved YOLOv7 Model

Underwater Small Target Detection Based on Improved YOLOv7 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 Article Underwater Small Target Detection Based on Improved YOLOv7 Model Shenming Qu, Can Cui, Jiale Duan, Yongyong Lu, Zilong Pang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4024158/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 21 You are reading this latest preprint version Abstract In the domain of marine environmental engineering, rapid and precise detection of underwater targets holds substantial significance. However, extant technologies for object detection are plagued by diminished accuracy and protracted processing speed when tasked with identifying occluded and diminutive targets in aquatic settings. In response to these impediments, this article has made innovative improvements on the basis of YOLOv7 to improve these issues. Firstly, we designed a G-ELAN module, which convolves low-level features and multiplies them element by element with high-level features, achieving multi-level feature fusion and effectively reducing target occlusion interference caused by underwater plankton. Secondly, the Residual-FasterNet module was proposed, which integrates residual strategies based on the T-shaped receptive field of FasterNet. This amalgamation enhances the model's ability to capture small target features. Evaluations conducted on the URPC2021 public dataset and the Zhanjiang competition dataset corroborate that our YOLOv7-GR model surpasses prevailing advanced methodologies in performance.The source code will be made publicly available at https://github.com/zzuilcc/YOLOv7-GR.git}{https://github.com/zzuilcc/YOLOv7-GR.git . Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Software Underwater image processing small target detection PConv FasterNet YOLOv7 Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 26 Apr, 2024 Reviews received at journal 25 Apr, 2024 Reviews received at journal 22 Apr, 2024 Reviews received at journal 21 Apr, 2024 Reviews received at journal 19 Apr, 2024 Reviews received at journal 18 Apr, 2024 Reviews received at journal 16 Apr, 2024 Reviewers agreed at journal 16 Apr, 2024 Reviewers agreed at journal 16 Apr, 2024 Reviewers agreed at journal 16 Apr, 2024 Reviewers agreed at journal 16 Apr, 2024 Reviews received at journal 15 Apr, 2024 Reviewers agreed at journal 15 Apr, 2024 Reviewers agreed at journal 15 Apr, 2024 Reviewers agreed at journal 15 Apr, 2024 Reviewers agreed at journal 15 Apr, 2024 Reviewers invited by journal 15 Apr, 2024 Editor assigned by journal 15 Apr, 2024 Editor invited by journal 19 Mar, 2024 Submission checks completed at journal 19 Mar, 2024 First submitted to journal 07 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-4024158","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":281801231,"identity":"8b447d28-a600-4dc3-ba10-6092d2732f84","order_by":0,"name":"Shenming Qu","email":"","orcid":"","institution":"Henan University","correspondingAuthor":false,"prefix":"","firstName":"Shenming","middleName":"","lastName":"Qu","suffix":""},{"id":281801232,"identity":"f9d67d5d-663b-4b96-beb1-0efcf1cc45e6","order_by":1,"name":"Can Cui","email":"","orcid":"","institution":"Henan University","correspondingAuthor":false,"prefix":"","firstName":"Can","middleName":"","lastName":"Cui","suffix":""},{"id":281801233,"identity":"f8ea2bb7-90d0-431e-8d26-762cacdc61f1","order_by":2,"name":"Jiale Duan","email":"","orcid":"","institution":"Henan University","correspondingAuthor":false,"prefix":"","firstName":"Jiale","middleName":"","lastName":"Duan","suffix":""},{"id":281801234,"identity":"52a29029-7d8f-4e17-93de-6c9a2b444e82","order_by":3,"name":"Yongyong Lu","email":"","orcid":"","institution":"Henan University","correspondingAuthor":false,"prefix":"","firstName":"Yongyong","middleName":"","lastName":"Lu","suffix":""},{"id":281801235,"identity":"a20526d0-1507-41ea-8a66-758fa6e6af2e","order_by":4,"name":"Zilong Pang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYBACxgYwZSFnAOEzE61Fwph4LVAgkbiBaC3M/cefSRf8kUjfzt57TIKhwjqxgf3sAfwOm5GQbDyDRyJ3Z8+5NAmGM+mJDTx5CQS0MBx8zCMhkbvhRo6ZBGPb4cQGCR4D/Fr6DzYc5jGQSDe4/wao5R8xWhqSGR/zJEgkGNzgAWppIEbLjDRm4xkHJAw3nMkxtkg4lm7cxpODX4shJMRs5A2OnzG88aHGWraf/QwBLQ3IcZEAxGx41QOBPAMpMT4KRsEoGAUjEwAAUgc/hFC2D9YAAAAASUVORK5CYII=","orcid":"","institution":"Henan University","correspondingAuthor":true,"prefix":"","firstName":"Zilong","middleName":"","lastName":"Pang","suffix":""}],"badges":[],"createdAt":"2024-03-07 11:02:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4024158/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4024158/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":53134102,"identity":"156af7e3-781d-4c3d-80b4-2b0eea8fadae","added_by":"auto","created_at":"2024-03-21 03:51:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":550302,"visible":true,"origin":"","legend":"","description":"","filename":"YOLOv7GRScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4024158/v1_covered_ce30c29d-fc94-4355-ac04-b53caddbe341.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Underwater Small Target Detection Based on Improved YOLOv7 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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Underwater image processing,small target detection, PConv, FasterNet, YOLOv7","lastPublishedDoi":"10.21203/rs.3.rs-4024158/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4024158/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the domain of marine environmental engineering, rapid and precise detection of underwater targets holds substantial significance. However, extant technologies for object detection are plagued by diminished accuracy and protracted processing speed when tasked with identifying occluded and diminutive targets in aquatic settings. In response to these impediments, this article has made innovative improvements on the basis of YOLOv7 to improve these issues. Firstly, we designed a G-ELAN module, which convolves low-level features and multiplies them element by element with high-level features, achieving multi-level feature fusion and effectively reducing target occlusion interference caused by underwater plankton. Secondly, the Residual-FasterNet module was proposed, which integrates residual strategies based on the T-shaped receptive field of FasterNet. This amalgamation enhances the model's ability to capture small target features. Evaluations conducted on the URPC2021 public dataset and the Zhanjiang competition dataset corroborate that our YOLOv7-GR model surpasses prevailing advanced methodologies in performance.The source code will be made publicly available at https://github.com/zzuilcc/YOLOv7-GR.git}{https://github.com/zzuilcc/YOLOv7-GR.git.","manuscriptTitle":"Underwater Small Target Detection Based on Improved YOLOv7 Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-21 03:42:58","doi":"10.21203/rs.3.rs-4024158/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-04-26T06:17:26+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-26T02:16:28+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-22T08:57:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-21T14:05:33+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-19T09:24:52+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-18T09:05:13+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-17T01:18:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"306eebe1-4123-402b-9711-5c383919cbb1","date":"2024-04-17T00:17:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"6b259790-d8f3-430a-a7c1-9cd736ca7769","date":"2024-04-16T10:44:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"aa15641c-9f16-4187-90f3-085cc3a90231","date":"2024-04-16T09:48:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"4190f345-4b7c-4a52-9a3d-57298778c0a0","date":"2024-04-16T05:33:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-16T01:31:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"b476308c-7d53-4f5f-b05d-85a27ba782f1","date":"2024-04-16T00:29:28+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"52083129-893b-4f02-862a-107e81457a58","date":"2024-04-15T16:33:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"936e1d83-c601-41af-a324-682b1e49b95f","date":"2024-04-15T13:39:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"198a2630-d240-434d-83f7-e507af9069c8","date":"2024-04-15T13:37:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-15T13:35:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-15T13:29:01+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-03-19T08:12:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-19T08:10:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-03-07T11:00:09+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"240556f3-9971-4e8d-a233-a2656b7df661","owner":[],"postedDate":"March 21st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":29672690,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":29672691,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2024-07-05T07:53:56+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-21 03:42:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4024158","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4024158","identity":"rs-4024158","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}