Learning from Motion. A Dynamic Feature Fusion Framework for Robust Agricultural Vision in Blurred Environments

Learning from Motion. A Dynamic Feature Fusion Framework for Robust Agricultural Vision in Blurred 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 Learning from Motion. A Dynamic Feature Fusion Framework for Robust Agricultural Vision in Blurred Environments Han Zhang, Yanwei Wang, Fang Li, Hongjun Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8760445/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 Computer vision for precision agriculture, particularly from unmanned aerial vehicles (UAVs), is frequently hampered by motion blur induced by wind and equipment vibration. Traditional approaches treat blur as noise to be removed or rely on computationally intensive restoration, limiting real-time deployment on edge devices. This study re-conceptualises motion blur not as mere degradation but as a source of learnable features characterising object dynamics. We introduce a Dynamic Fuzzy Robust Convolution (DFRC) module, a plug-in enhancement for detection frameworks, which adaptively fuses multi-scale features with synthetically generated fuzzy cues via a transparency-aware mechanism. A key innovation is a parallel CUDA kernel for efficient non-linear interpolation and rotation of feature tensors, preventing boundary overflow and achieving a 38.4× speedup over CPU implementations. Trained on a purpose-built wheat pest dataset (WheatBlur-3K) with paired clear and synthetically blurred images (including uniform and target-localised blur), our YOLOv11-based model demonstrates robust performance. On blurred test sets, it achieves an [email protected] of 86.4\%, a 26.1\% improvement over the baseline, while maintaining a real-time inference speed of 47 FPS. The framework retains effectiveness in adverse conditions like rain, with performance degradation below 8\%. This work provides a practical, efficient solution for blur-robust agricultural monitoring, shifting the paradigm from blur removal to blur-aware perception. Code and data are available at \url{https://gitcode.com/2401_85342087/yolo11-fuzzy-conv.git}. Artificial Intelligence and Machine Learning YOLOv11 Wheat Disease and Pest Detection Dynamic fuzzy robust convolution CUDA Parallel Computing Full Text Additional Declarations The authors declare no competing interests. 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-8760445","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":584022112,"identity":"f57da899-0a1f-428e-bb68-04bc43ae4286","order_by":0,"name":"Han Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtElEQVRIiWNgGAWjYDACCQYGAx4GGx5+/gbStKTJSM44QIIWBh6GwzYGDQlE6pCf3WNQ8LbtPI8BwwHGDx9ziNDCOOdYguGcM7d5zJkbmCVnbiNCC7NE8gFjnorbPJYNB9iYeYnRwiaR2GDMY3COx+BAApFaeCC2HCBBi4REGsgvyTySMw42E+cX+Rk5ZgZv2+zs+fmbD374SIwWIGAzgNCMDcSpBwLmB0QrHQWjYBSMgpEJADG5MWFJpR4PAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-0169-8140","institution":"Changji University","correspondingAuthor":true,"prefix":"","firstName":"Han","middleName":"","lastName":"Zhang","suffix":""},{"id":584022113,"identity":"e22c8847-a21d-47f7-a8e8-9aa0b5b75df6","order_by":1,"name":"Yanwei Wang","email":"","orcid":"","institution":"Changji University","correspondingAuthor":false,"prefix":"","firstName":"Yanwei","middleName":"","lastName":"Wang","suffix":""},{"id":584022114,"identity":"001df787-a136-4abc-b242-49f56df8739c","order_by":2,"name":"Fang Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie3PsYrCQBCA4TkCqUbSHSMH7itMWLhKuFfJIljl4MqUESWVDxAxD2F55YSANrEXbISrBeFawbtgY+VuKbh/MdV8DAPg8z1iBMAIQ4xUI3LK3Ml40C9DU5etIwGERvMOddObOQi1nPPXsQhMvp+fpJeDil7lPnmp1klctaGZVNuV9L8hXiyT+ySgkWjM0EzhcyVxCwnvLSQkk2tkMgWkB/mfdoLXK6yRUpDahRCNu1+SAeGa67wl+y+qTN/5WFzwYzP9+T1nQxW9WUj3Dt9eta53BQenNZ/P53ve/gCQo0dR1/XcVgAAAABJRU5ErkJggg==","orcid":"","institution":"Changji University","correspondingAuthor":true,"prefix":"","firstName":"Fang","middleName":"","lastName":"Li","suffix":""},{"id":584022115,"identity":"a71f6f7c-a6f0-48b4-b6e5-b45613c5ca1b","order_by":3,"name":"Hongjun Wang","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Hongjun","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2026-02-02 04:42:12","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8760445/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8760445/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101753788,"identity":"f59d60bc-73ef-44bc-afd6-6bf7d519109a","added_by":"auto","created_at":"2026-02-03 10:40:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2335407,"visible":true,"origin":"","legend":"","description":"","filename":"LearningfromMotionADynamicFeatureFusionFrameworkforRobustAgriculturalVisioninBlurredEnvironments.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8760445/v1_covered_3e7f5d08-3e55-43f1-8251-0c88571ee0f3.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLearning from Motion. A Dynamic Feature Fusion Framework for Robust Agricultural Vision in Blurred Environments\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Changji University","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":"YOLOv11, Wheat Disease and Pest Detection, Dynamic fuzzy robust convolution, CUDA Parallel Computing","lastPublishedDoi":"10.21203/rs.3.rs-8760445/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8760445/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eComputer vision for precision agriculture, particularly from unmanned aerial vehicles (UAVs), is frequently hampered by motion blur induced by wind and equipment vibration. Traditional approaches treat blur as noise to be removed or rely on computationally intensive restoration, limiting real-time deployment on edge devices. This study re-conceptualises motion blur not as mere degradation but as a source of learnable features characterising object dynamics. We introduce a Dynamic Fuzzy Robust Convolution (DFRC) module, a plug-in enhancement for detection frameworks, which adaptively fuses multi-scale features with synthetically generated fuzzy cues via a transparency-aware mechanism. A key innovation is a parallel CUDA kernel for efficient non-linear interpolation and rotation of feature tensors, preventing boundary overflow and achieving a 38.4× speedup over CPU implementations. Trained on a purpose-built wheat pest dataset (WheatBlur-3K) with paired clear and synthetically blurred images (including uniform and target-localised blur), our YOLOv11-based model demonstrates robust performance. On blurred test sets, it achieves an [email protected] of 86.4\\%, a 26.1\\% improvement over the baseline, while maintaining a real-time inference speed of 47 FPS. The framework retains effectiveness in adverse conditions like rain, with performance degradation below 8\\%. This work provides a practical, efficient solution for blur-robust agricultural monitoring, shifting the paradigm from blur removal to blur-aware perception. Code and data are available at \\url{https://gitcode.com/2401_85342087/yolo11-fuzzy-conv.git}.\u003c/p\u003e","manuscriptTitle":"Learning from Motion. A Dynamic Feature Fusion Framework for Robust Agricultural Vision in Blurred Environments","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-03 03:50:06","doi":"10.21203/rs.3.rs-8760445/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":"c454ce85-6852-4635-b5e2-59c21d50627f","owner":[],"postedDate":"February 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62128699,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-02-06T05:50:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-03 03:50:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8760445","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8760445","identity":"rs-8760445","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}