Enhanced Object Detection in Maritime Vision: Modified YOLOv8 Architecture and SAHI-Based Inference

Enhanced Object Detection in Maritime Vision: Modified YOLOv8 Architecture and SAHI-Based Inference | 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 Enhanced Object Detection in Maritime Vision: Modified YOLOv8 Architecture and SAHI-Based Inference José Luis Mela, Carlos Garcia-Sanchez This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7230823/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Object detection in maritime environments poses particular challenges due to dynamic environmental conditions, variability in object scale, and computational constraints of edge devices. In this study, a modified YOLOv8-based architecture optimized for small object detection is proposed. The proposal integrates Dynamic Convolution (DyConv) layers, Efficient Channel Attention (ECA) in the C2f modules, an additional P2/4-scale detection head, a multiscale fusion with spatial and channel attention, and an enhanced version of the SPPF module. In addition, the Slicing Aided Hyper Inference (SAHI) technique is incorporated to improve detection sensitivity during inference. Experiments performed on the Datasense@CRAS dataset demonstrate significant improvements, especially our proposal YOLOv8n-modified architecture obtained an average increase of +1.19 % in mAP50 and +2.09 % in mAP50:95, while the YOLOv8l-Modified variant achieved improvements of +1.88 % and +3.60 %, respectively. These gains are especially notable in small object classes, such as Small and Sail Boats, where increases of up to +7.6 % and +10.5 % were recorded in mAP50 and mAP50:95. The integration of SAHI increased by more than $2\times$ the number of objects detected in complex scenarios, evidencing its usefulness for maritime environments. Finally, the feasibility of implementation on edge devices such as NVIDIA Jetson AGX Orin is validated, where our model YOLOv8l-Modified in FP16 offers the best balance between accuracy, real-time performance, and energy efficiency. This shows that the proposed architecture is particularly effective in detecting small objects, increasing the number of objects detected and the confidence level to improve autonomous navigation. It addresses the unique challenges of maritime environments, including variable lighting, occlusion, and the need for efficient onboard processing in USVs and autonomous platforms. Maritime object detection YOLOv8 Dynamic convolution SAHI Unmanned surface vehicle Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-7230823","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":499220003,"identity":"c96b7295-681f-4ee3-aedb-318b7b9ac3e4","order_by":0,"name":"José Luis Mela","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAoUlEQVRIiWNgGAWjYBACxgYGxgMMFSRqYTjAcIZUmw4wtpGinHna4QMHfs47LK/bwHz4A3EOm52WcLB322HDbQfY0iSI1JJjcIB32+EEswM8ZsQ5jHF2/oeDf+eAtPB/JtZhOQyHeRvAtjAQ67A0g8Myx9INtx1mMyNOi+Hs5IcP39RYy5sdb35MnMMMG2AsZqLUA4E8sQpHwSgYBaNgBAMApKUzO1/s0iwAAAAASUVORK5CYII=","orcid":"","institution":"Complutense University of Madrid","correspondingAuthor":true,"prefix":"","firstName":"José","middleName":"Luis","lastName":"Mela","suffix":""},{"id":499220004,"identity":"ec967f66-1016-4a9d-b643-7ccd1082818d","order_by":1,"name":"Carlos Garcia-Sanchez","email":"","orcid":"","institution":"Complutense University of Madrid","correspondingAuthor":false,"prefix":"","firstName":"Carlos","middleName":"","lastName":"Garcia-Sanchez","suffix":""}],"badges":[],"createdAt":"2025-07-28 07:23:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7230823/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7230823/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92592572,"identity":"0b77ee83-b0c1-49ef-8a72-e9e7c404f820","added_by":"auto","created_at":"2025-10-01 12:17:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1393525,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7230823/v1_covered_298f4d95-ede7-4c03-a79d-9ba0b1545edc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Object Detection in Maritime Vision: Modified YOLOv8 Architecture and SAHI-Based Inference","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":" Maritime object detection, YOLOv8, Dynamic convolution, SAHI, Unmanned surface vehicle","lastPublishedDoi":"10.21203/rs.3.rs-7230823/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7230823/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Object detection in maritime environments poses particular challenges due to dynamic environmental conditions, variability in object scale, and computational constraints of edge devices. In this study, a modified YOLOv8-based architecture optimized for small object detection is proposed. The proposal integrates Dynamic Convolution (DyConv) layers, Efficient Channel Attention (ECA) in the C2f modules, an additional P2/4-scale detection head, a multiscale fusion with spatial and channel attention, and an enhanced version of the SPPF module. In addition, the Slicing Aided Hyper Inference (SAHI) technique is incorporated to improve detection sensitivity during inference. Experiments performed on the Datasense@CRAS dataset demonstrate significant improvements, especially our proposal YOLOv8n-modified architecture obtained an average increase of +1.19 \\% in mAP50 and +2.09 \\% in mAP50:95, while the YOLOv8l-Modified variant achieved improvements of +1.88 \\% and +3.60 \\%, respectively. These gains are especially notable in small object classes, such as Small and Sail Boats, where increases of up to +7.6 \\% and +10.5 \\% were recorded in mAP50 and mAP50:95. The integration of SAHI increased by more than $2\\times$ the number of objects detected in complex scenarios, evidencing its usefulness for maritime environments. Finally, the feasibility of implementation on edge devices such as NVIDIA Jetson AGX Orin is validated, where our model YOLOv8l-Modified in FP16 offers the best balance between accuracy, real-time performance, and energy efficiency. This shows that the proposed architecture is particularly effective in detecting small objects, increasing the number of objects detected and the confidence level to improve autonomous navigation. It addresses the unique challenges of maritime environments, including variable lighting, occlusion, and the need for efficient onboard processing in USVs and autonomous platforms.","manuscriptTitle":"Enhanced Object Detection in Maritime Vision: Modified YOLOv8 Architecture and SAHI-Based Inference","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-14 18:23:34","doi":"10.21203/rs.3.rs-7230823/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1d312f15-2459-4ba4-a561-98574f312be8","owner":[],"postedDate":"August 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-01T12:08:51+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-14 18:23:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7230823","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7230823","identity":"rs-7230823","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}