GSBF-YOLO: a lightweight model for tomato ripeness detection in natural environments

GSBF-YOLO: a lightweight model for tomato ripeness detection in natural environments | 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 GSBF-YOLO: a lightweight model for tomato ripeness detection in natural environments Fengqi Hao, Zuyao Zhang, Dexin Ma, Hoiio Kong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4724627/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Jan, 2025 Read the published version in Journal of Real-Time Image Processing → Version 1 posted 14 You are reading this latest preprint version Abstract Accurate tomato ripeness detection is essential for optimizing harvest timing and maximizing yield. Deep learning-based object detection has proven effective in this task. However, many existing algorithms have numerous parameters and substantial computational demands, making them unsuitable for agricultural environments with limited computational resources. Additionally, accurate detection becomes challenging with overlapping fruits, leaf occlusion, or complex backgrounds. To address these issues, this paper proposes a lightweight detection model, GSBF-YOLO. This model designs the GSim module to reduce parameters while maintaining detection accuracy. The C3Ghost module further reduces parameter count by replacing the traditional C3 module. The PANet multi-scale feature fusion network in the neck is replaced with the Bi-directional Feature Pyramid Network (BiFPN), which adjusts weights based on the importance of input features. Lastly, the fine-tuned FocalEIOU Loss function is used to calculate the bounding box regression loss, enhancing the model's ability to adjust the weights of high-quality anchor boxes for better detection of targets in occlusion scenarios. Experimental results show that GSBF-YOLO reduces parameters and computational load by 42% and 45%, respectively, while mean Average Precision (mAP) increases by 1.9% and 1.6% on two datasets. The model achieves 110 Frames Per Second (FPS), meeting real-time detection requirements, and has fewer parameters and higher accuracy compared to models like YOLOv8. The research indicates that the proposed lightweight model can effectively detect tomato ripeness in natural environments. Lightweight Deep learning Tomato ripeness Object detection Real-time detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 20 Jan, 2025 Read the published version in Journal of Real-Time Image Processing → Version 1 posted Editorial decision: Revision requested 16 Oct, 2024 Reviews received at journal 15 Oct, 2024 Reviews received at journal 05 Oct, 2024 Reviewers agreed at journal 04 Oct, 2024 Reviewers agreed at journal 29 Sep, 2024 Reviewers agreed at journal 29 Sep, 2024 Reviewers agreed at journal 27 Sep, 2024 Reviewers agreed at journal 27 Sep, 2024 Reviews received at journal 15 Aug, 2024 Reviewers agreed at journal 10 Aug, 2024 Reviewers invited by journal 24 Jul, 2024 Editor assigned by journal 16 Jul, 2024 Submission checks completed at journal 16 Jul, 2024 First submitted to journal 11 Jul, 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-4724627","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":333326637,"identity":"296a367f-b851-4a22-923f-08a8f14504ad","order_by":0,"name":"Fengqi Hao","email":"","orcid":"","institution":"Qilu University of Technology (Shandong Academy of Sciences)","correspondingAuthor":false,"prefix":"","firstName":"Fengqi","middleName":"","lastName":"Hao","suffix":""},{"id":333326638,"identity":"8744ec8b-9dd6-48c2-a01e-55dc56677696","order_by":1,"name":"Zuyao Zhang","email":"","orcid":"","institution":"Qilu University of Technology (Shandong Academy of Sciences)","correspondingAuthor":false,"prefix":"","firstName":"Zuyao","middleName":"","lastName":"Zhang","suffix":""},{"id":333326639,"identity":"ccc235a2-eb24-499d-a417-4f48e3e730d2","order_by":2,"name":"Dexin Ma","email":"","orcid":"","institution":"Qingdao Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Dexin","middleName":"","lastName":"Ma","suffix":""},{"id":333326640,"identity":"cc6a6a9a-b149-443c-a277-d7f67dd6b645","order_by":3,"name":"Hoiio Kong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIiWNgGAWjYBACA2Y2EGXDwAbhMxOtJY2BjY1oLRDjDzMwEK3FnJ0t8XHBr/PyfPI9ZhIMFdaJDWKHD+DVYtnMdth4Zt9twzY2HqCWM+mJDdJpCfgddpi9TZq353YCG0gLY9thoJYcA2K0nINq+UeUFrZj0jw/DkC1NBCnJdmYtyEZ6Je0YouEY+nGbQT9cv6Y4WOeP3by8s2HN974UGMt2y+dfACvFjBgbAORHAYMIOPZCKsHgT8ggv0BcYpHwSgYBaNgxAEAqSs8WzyH+6sAAAAASUVORK5CYII=","orcid":"","institution":"City University of Macau","correspondingAuthor":true,"prefix":"","firstName":"Hoiio","middleName":"","lastName":"Kong","suffix":""}],"badges":[],"createdAt":"2024-07-11 14:00:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4724627/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4724627/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11554-025-01624-y","type":"published","date":"2025-01-20T15:57:03+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74858600,"identity":"9b2b2340-7242-4a3c-b163-de91409da8d7","added_by":"auto","created_at":"2025-01-27 16:12:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6874544,"visible":true,"origin":"","legend":"","description":"","filename":"snarticletemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4724627/v1_covered_e371d7e9-23b1-4e2d-b8bc-aa7ee098c107.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GSBF-YOLO: a lightweight model for tomato ripeness detection in natural environments","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":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Lightweight, Deep learning, Tomato ripeness, Object detection, Real-time detection","lastPublishedDoi":"10.21203/rs.3.rs-4724627/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4724627/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate tomato ripeness detection is essential for optimizing harvest timing and maximizing yield. Deep learning-based object detection has proven effective in this task. However, many existing algorithms have numerous parameters and substantial computational demands, making them unsuitable for agricultural environments with limited computational resources. Additionally, accurate detection becomes challenging with overlapping fruits, leaf occlusion, or complex backgrounds. To address these issues, this paper proposes a lightweight detection model, GSBF-YOLO. This model designs the GSim module to reduce parameters while maintaining detection accuracy. The C3Ghost module further reduces parameter count by replacing the traditional C3 module. The PANet multi-scale feature fusion network in the neck is replaced with the Bi-directional Feature Pyramid Network (BiFPN), which adjusts weights based on the importance of input features. Lastly, the fine-tuned FocalEIOU Loss function is used to calculate the bounding box regression loss, enhancing the model's ability to adjust the weights of high-quality anchor boxes for better detection of targets in occlusion scenarios. Experimental results show that GSBF-YOLO reduces parameters and computational load by 42% and 45%, respectively, while mean Average Precision (mAP) increases by 1.9% and 1.6% on two datasets. The model achieves 110 Frames Per Second (FPS), meeting real-time detection requirements, and has fewer parameters and higher accuracy compared to models like YOLOv8. The research indicates that the proposed lightweight model can effectively detect tomato ripeness in natural environments.","manuscriptTitle":"GSBF-YOLO: a lightweight model for tomato ripeness detection in natural environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-09 08:49:04","doi":"10.21203/rs.3.rs-4724627/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-16T19:36:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-16T02:02:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-05T05:19:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"158338398059483789182785521855936079732","date":"2024-10-05T01:19:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"744736392947702896996659897634001973","date":"2024-09-29T17:48:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"78362015870845767160563070080637038656","date":"2024-09-29T09:36:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"149742095376123509185787391166564628719","date":"2024-09-27T23:42:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"123352257302922032200052331352383160817","date":"2024-09-27T18:07:14+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-15T11:13:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"95245351795466660076733444298289794220","date":"2024-08-11T00:19:11+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-24T16:22:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-16T13:42:51+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-16T13:42:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Real-Time Image Processing","date":"2024-07-11T13:58:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-real-time-image-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rtip","sideBox":"Learn more about [Journal of Real-Time Image Processing](http://link.springer.com/journal/11554)","snPcode":"11554","submissionUrl":"https://submission.nature.com/new-submission/11554/3","title":"Journal of Real-Time Image Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"19f95317-84f1-438b-86ee-bed089f9803c","owner":[],"postedDate":"August 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-01-27T16:06:54+00:00","versionOfRecord":{"articleIdentity":"rs-4724627","link":"https://doi.org/10.1007/s11554-025-01624-y","journal":{"identity":"journal-of-real-time-image-processing","isVorOnly":false,"title":"Journal of Real-Time Image Processing"},"publishedOn":"2025-01-20 15:57:03","publishedOnDateReadable":"January 20th, 2025"},"versionCreatedAt":"2024-08-09 08:49:04","video":"","vorDoi":"10.1007/s11554-025-01624-y","vorDoiUrl":"https://doi.org/10.1007/s11554-025-01624-y","workflowStages":[]},"version":"v1","identity":"rs-4724627","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4724627","identity":"rs-4724627","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}