SAF-YOLO: Super-Resolution Augmented Detection Model with Visual State Space Enhancement for Safflower Filament Picking

SAF-YOLO: Super-Resolution Augmented Detection Model with Visual State Space Enhancement for Safflower Filament Picking | 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 SAF-YOLO: Super-Resolution Augmented Detection Model with Visual State Space Enhancement for Safflower Filament Picking Mengyu Duan, Xiaorong Wang, Linwei Qiu, Menghao Li, Jinrong Chen, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8208511/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Apr, 2026 Read the published version in Precision Agriculture → Version 1 posted You are reading this latest preprint version Abstract Cluttered backgrounds, variable shooting angles, and fluctuating lighting in safflower fields frequently induce missed or false detections of filaments by picking robots, especially for small and imbalanced targets. To address these inherent limitations, we propose SAF-YOLO, a novel detector tailored for safflower filament detection. It incorporates three complementary innovations: (1) A causal Visual State Space Model (VSSM)-based VSS-SPPF module integrated into the Backbone, enhancing spatial context modeling to separate filaments from noisy backgrounds; (2) An Asymptotic Feature Pyramid Network (AFPN) structure in the Neck, optimizing feature adaptive aggregation to boost multi-scale targets sensitivity; (3) An auxiliary Super-Resolution Self-Supervised (SRSS) branch, addressing small and imbalanced target distribution by enabling fine-grained feature learning via high-resolution reconstruction during training, while being discarded at inference to avoid computational overhead. Experimental results demonstrate SAF-YOLO achieves 90.1% Precision, 85.9% Recall, and 93.3% mAP. This outperforms the popular YOLO variants, including YOLOv5/v7/v8/v11 (mAP +4.1%-8.0%), and mainstream small-object detectors (e.g., SSD, Faster R-CNN, CFINet, CFPT, and InSPyReNet; mAP +7.9%-26.2%). Our SAF-YOLO can effectively solve safflower filament detection challenges in complex fields, supporting robotic precision picking. Safflower Harvesting Object Detection Visual State-Space Model Super Resolution Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Apr, 2026 Read the published version in Precision Agriculture → 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-8208511","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":561973416,"identity":"da990357-9131-4781-a298-3dde124ed137","order_by":0,"name":"Mengyu Duan","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"Mengyu","middleName":"","lastName":"Duan","suffix":""},{"id":561973420,"identity":"2d23d826-9bb9-4124-b5d9-86649906de60","order_by":1,"name":"Xiaorong Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYDACZmTOBwY2EGVAvBbGGURpQdHOA6HxazE4zvzwcUXFHbsNx88efm3bxpfYwN68TYKh5g5OLZLNbMaGZ848S95wJi/NOucMW2IDz7EyCYZjz3Bq4WdmMJNsbDucbHYgx8w4pwKoRSLHTIKx4TBOLWzM7N8gWs6/MTO2MABqkX+DXws/Mw/YFjuzGznGjxnAtvDg1yLZzFNs2HDmcIL9jTdmjD1n2IzbeNKKLRKO4dZicP74xocNFYftJftzjD/8bDsm289+eOONDzW4tcBAYgPQXxIMDMcgkZlAUAMDgz0QM39gYKghQu0oGAWjYBSMNAAAgn5SwXOw9LQAAAAASUVORK5CYII=","orcid":"","institution":"Xinjiang University","correspondingAuthor":true,"prefix":"","firstName":"Xiaorong","middleName":"","lastName":"Wang","suffix":""},{"id":561973421,"identity":"f3aa48a5-4048-4288-8055-dd6410dc6ed5","order_by":2,"name":"Linwei Qiu","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Linwei","middleName":"","lastName":"Qiu","suffix":""},{"id":561973425,"identity":"5c3d1644-686f-4731-813d-1b35a92de6c6","order_by":3,"name":"Menghao Li","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"Menghao","middleName":"","lastName":"Li","suffix":""},{"id":561973428,"identity":"e10d0552-fcfd-484b-9650-c2787811f925","order_by":4,"name":"Jinrong Chen","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"Jinrong","middleName":"","lastName":"Chen","suffix":""},{"id":561973436,"identity":"af4a0f8a-e6c3-4019-bcf1-d6f91224067c","order_by":5,"name":"He Liang","email":"","orcid":"","institution":"Xinjiang University","correspondingAuthor":false,"prefix":"","firstName":"He","middleName":"","lastName":"Liang","suffix":""}],"badges":[],"createdAt":"2025-11-26 04:38:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8208511/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8208511/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11119-026-10357-2","type":"published","date":"2026-04-27T15:57:11+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98513110,"identity":"e72a8dc5-269d-4e98-9cea-10c84f3c986e","added_by":"auto","created_at":"2025-12-18 12:06:13","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6951,"visible":true,"origin":"","legend":"","description":"","filename":"6b5ed52120864a469edd780c0bdf02d8.json","url":"https://assets-eu.researchsquare.com/files/rs-8208511/v1/5c9c779285f55ad7fb685999.json"},{"id":108437569,"identity":"516c14a8-3ba4-4469-af45-cee75389cb9a","added_by":"auto","created_at":"2026-05-04 15:59:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1794530,"visible":true,"origin":"","legend":"","description":"","filename":"SAFYOLO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8208511/v1_covered_9bd5eacd-cb67-4ec0-bbfa-d17e4799f48f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SAF-YOLO: Super-Resolution Augmented Detection Model with Visual State Space Enhancement for Safflower Filament Picking","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Safflower Harvesting, Object Detection, Visual State-Space Model, Super Resolution","lastPublishedDoi":"10.21203/rs.3.rs-8208511/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8208511/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Cluttered backgrounds, variable shooting angles, and fluctuating lighting in safflower fields frequently induce missed or false detections of filaments by picking robots, especially for small and imbalanced targets. To address these inherent limitations, we propose SAF-YOLO, a novel detector tailored for safflower filament detection. It incorporates three complementary innovations: (1) A causal Visual State Space Model (VSSM)-based VSS-SPPF module integrated into the Backbone, enhancing spatial context modeling to separate filaments from noisy backgrounds; (2) An Asymptotic Feature Pyramid Network (AFPN) structure in the Neck, optimizing feature adaptive aggregation to boost multi-scale targets sensitivity; (3) An auxiliary Super-Resolution Self-Supervised (SRSS) branch, addressing small and imbalanced target distribution by enabling fine-grained feature learning via high-resolution reconstruction during training, while being discarded at inference to avoid computational overhead. Experimental results demonstrate SAF-YOLO achieves 90.1% Precision, 85.9% Recall, and 93.3% mAP. This outperforms the popular YOLO variants, including YOLOv5/v7/v8/v11 (mAP +4.1%-8.0%), and mainstream small-object detectors (e.g., SSD, Faster R-CNN, CFINet, CFPT, and InSPyReNet; mAP +7.9%-26.2%). Our SAF-YOLO can effectively solve safflower filament detection challenges in complex fields, supporting robotic precision picking.","manuscriptTitle":"SAF-YOLO: Super-Resolution Augmented Detection Model with Visual State Space Enhancement for Safflower Filament Picking","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-18 12:06:09","doi":"10.21203/rs.3.rs-8208511/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":"a563384a-109b-42f7-9c03-3cde83c8ee29","owner":[],"postedDate":"December 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-04T15:59:08+00:00","versionOfRecord":{"articleIdentity":"rs-8208511","link":"https://doi.org/10.1007/s11119-026-10357-2","journal":{"identity":"precision-agriculture","isVorOnly":false,"title":"Precision Agriculture"},"publishedOn":"2026-04-27 15:57:11","publishedOnDateReadable":"April 27th, 2026"},"versionCreatedAt":"2025-12-18 12:06:09","video":"","vorDoi":"10.1007/s11119-026-10357-2","vorDoiUrl":"https://doi.org/10.1007/s11119-026-10357-2","workflowStages":[]},"version":"v1","identity":"rs-8208511","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8208511","identity":"rs-8208511","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}