Lightweight apple detection method in complex environment based on YOLOv10s-Star

Lightweight apple detection method in complex environment based on YOLOv10s-Star | 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 Lightweight apple detection method in complex environment based on YOLOv10s-Star Xingda WANG, Yanfei ZHANG, Lantao GUO, Bing ZHAO, Jinliang GONG This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6211772/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 In order to achieve high-precision and fast detection of apple targets in complex orchard environments, this study proposed a lightweight target recognition method YOLOv10s-Star. First, based on the YOLOv10s model, StarNet is used as the backbone network to reduce the number of parameters and calculations, and the SCSA attention mechanism is added to the PSA module. By co-focusing on the spatial and channel attention mechanisms, the feature extraction ability of the model is enhanced; the improved BiFPN module structure is used in the neck network to achieve full fusion and utilization of the deep feature map target semantic information and the shallow feature map target position information, thereby improving the detection accuracy; finally, the DyHead detection head is designed to replace the original detection head to achieve scale perception, spatial perception, and task perception, thereby improving the accuracy and efficiency of the target detection task. Experimental results show that the mAP value of the YOLOv10s-Star model is 92.4%, the number of parameters is 5.06M, the amount of calculation is 12.9G, and the average inference speed is 126.3 fps. It maintains high detection accuracy while being lightweight and improves the detection speed. It is suitable for deployment on embedded devices of apple picking robots, laying the foundation for the realization of intelligent apple picking. Deep learning YOLOv10s Apple Lightweight Detection speed Target detection 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-6211772","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":435947107,"identity":"428ef568-4572-4a3e-b258-9ed0fc20e88a","order_by":0,"name":"Xingda WANG","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYBACNvbG5gcfDGyY+ZmZDxCnhY/ncJvhjIo0dsl2tgTitMhJpDdIc5w5xG9wnseASIfxHGwwZmw7IM1wmOfjjTcMdnK6DYS0sDc2PC5su2PM2My72XIOQ7Kx2QFibJnZ9iyZmZl3mzQPw4HEbQS1SCQ2SPO2Ha5vY+Z5RoIWnjOHmXmYediI1MJzEBzIzBLMbMaWcwyI8It8e/tjcFTanz/88MabCjs5glpQgASxUYOshVQdo2AUjIJRMCIAAOT7QImblVCmAAAAAElFTkSuQmCC","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Xingda","middleName":"","lastName":"WANG","suffix":""},{"id":435947108,"identity":"2022e841-8271-430b-92dc-e145bccf7f04","order_by":1,"name":"Yanfei ZHANG","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yanfei","middleName":"","lastName":"ZHANG","suffix":""},{"id":435947109,"identity":"fe889c55-644a-47b6-adea-64aca8b784a0","order_by":2,"name":"Lantao GUO","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Lantao","middleName":"","lastName":"GUO","suffix":""},{"id":435947110,"identity":"18fc7b6c-a210-4e19-b9f8-034d953a26bb","order_by":3,"name":"Bing ZHAO","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bing","middleName":"","lastName":"ZHAO","suffix":""},{"id":435947111,"identity":"58313e85-ff24-49ba-8504-10cd688f631e","order_by":4,"name":"Jinliang GONG","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinliang","middleName":"","lastName":"GONG","suffix":""}],"badges":[],"createdAt":"2025-03-12 11:53:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6211772/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6211772/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82929160,"identity":"de8bf2ac-1f37-4ab8-9c6c-b67d123d12ab","added_by":"auto","created_at":"2025-05-16 21:31:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":942503,"visible":true,"origin":"","legend":"","description":"","filename":"LightweightappledetectionmethodincomplexenvironmentbasedonYOLOv10sStar.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6211772/v1_covered_2f262f06-270b-4928-9128-a7a1c45c8305.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Lightweight apple detection method in complex environment based on YOLOv10s-Star","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":"Deep learning, YOLOv10s, Apple, Lightweight, Detection speed, Target detection","lastPublishedDoi":"10.21203/rs.3.rs-6211772/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6211772/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn order to achieve high-precision and fast detection of apple targets in complex orchard environments, this study proposed a lightweight target recognition method YOLOv10s-Star. First, based on the YOLOv10s model, StarNet is used as the backbone network to reduce the number of parameters and calculations, and the SCSA attention mechanism is added to the PSA module. By co-focusing on the spatial and channel attention mechanisms, the feature extraction ability of the model is enhanced; the improved BiFPN module structure is used in the neck network to achieve full fusion and utilization of the deep feature map target semantic information and the shallow feature map target position information, thereby improving the detection accuracy; finally, the DyHead detection head is designed to replace the original detection head to achieve scale perception, spatial perception, and task perception, thereby improving the accuracy and efficiency of the target detection task. Experimental results show that the mAP value of the YOLOv10s-Star model is 92.4%, the number of parameters is 5.06M, the amount of calculation is 12.9G, and the average inference speed is 126.3 fps. It maintains high detection accuracy while being lightweight and improves the detection speed. It is suitable for deployment on embedded devices of apple picking robots, laying the foundation for the realization of intelligent apple picking.\u003c/p\u003e","manuscriptTitle":"Lightweight apple detection method in complex environment based on YOLOv10s-Star","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-31 03:26:30","doi":"10.21203/rs.3.rs-6211772/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":"41e82515-9168-436e-b01b-5bac3d510c2d","owner":[],"postedDate":"March 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-16T21:23:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-31 03:26:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6211772","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6211772","identity":"rs-6211772","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}