A Dual Dynamic Feature-based Deep Learning and Computer Vision–Based Model for Multi-Object Classification Using Geospatial Satellite Imagery

A Dual Dynamic Feature-based Deep Learning and Computer Vision–Based Model for Multi-Object Classification Using Geospatial Satellite Imagery | 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 A Dual Dynamic Feature-based Deep Learning and Computer Vision–Based Model for Multi-Object Classification Using Geospatial Satellite Imagery Doaa Mohey Eldin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8992042/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 This paper introduces a Dual Dynamic Feature-based Deep Learning and Computer Vision–Based Model for Multi-Object Classification Using Geospatial Satellite imagery using dynamic feature extraction neural network and selecting the feature selection multi object classification images. The proposed framework is developed multi neural networks for features and advanced YOLOv8 architecture to enhance detection accuracy and efficiency for real-world objects and counting objects such as people, vehicles, and trees across various imaging modalities. The integration of high-resolution data from satellite systems offers a comprehensive view of both ground-level and aerial environments, supporting large-scale object detection and geospatial analysis. To address the limitations of conventional single-source models, the proposed dynamic model utilizes adaptive feature extraction and multi-scale learning strategies, which improve generalization across different resolutions and environmental conditions. Experimental results show that the model applies to two verified datasets that achieves superior performance in terms of detection precision and computational efficiency, confirming its potential for practical applications in urban monitoring, and environmental surveillance. This paper contributes to the advancement of Dual Dynamic Feature-based Deep Learning and Computer Vision–Based AI Model to geospatial analytics by providing multi neural networks to identify multiple object types. The experimental accuracy results for multi object classification via two satellite imagery datasets achieve 99.9%. Artificial intelligence (AI) Geospatial images Deep learning Computer vision multi-object classification Optical Drone Satellite 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-8992042","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":598395146,"identity":"64ba6714-1947-49ac-ad5b-13b52a3a1ef4","order_by":0,"name":"Doaa Mohey Eldin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYDCCAwwMzEBKjo29sfEBkMHDR6wWY36ew4cNQFrYiNWSOHNGWpoESICgFr4D3ImPCyoOM244kGNW+TXHToaNgfnhoxt4tEge4N1sPOPMYWaDA2fMbstuSwY6jM3YOAePFoMDvNukedsOsxkc7DG7LbmNGaiFh02asJZ/h3kMDvOYFUtuqydWS8NhCck2tjTGj9sOE9YieRjoF55j6Qb8PMyHpRm3HedhYybgF77jvRsf89RY17fJP2z8+HNbtT0/e/PDx/i0gCOFgaEZwuZBiBAEdWCS8QdxqkfBKBgFo2CEAQALPEd+XMwx0gAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Doaa","middleName":"Mohey","lastName":"Eldin","suffix":""}],"badges":[],"createdAt":"2026-02-28 02:27:51","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-8992042/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8992042/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104401059,"identity":"33065313-2c66-4b2b-a841-573d461ed738","added_by":"auto","created_at":"2026-03-11 12:11:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":808001,"visible":true,"origin":"","legend":"","description":"","filename":"paper4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8992042/v1_covered_e053548b-8a3d-4413-8ec6-9e19e7dc6932.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eA Dual Dynamic Feature-based Deep Learning and Computer Vision–Based Model for Multi-Object Classification Using Geospatial Satellite Imagery\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Artificial intelligence (AI), Geospatial images, Deep learning, Computer vision, multi-object classification, Optical, Drone, Satellite","lastPublishedDoi":"10.21203/rs.3.rs-8992042/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8992042/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper introduces a Dual Dynamic Feature-based Deep Learning and Computer Vision\u0026ndash;Based Model for Multi-Object Classification Using Geospatial Satellite imagery using dynamic feature extraction neural network and selecting the feature selection multi object classification images. The proposed framework is developed multi neural networks for features and advanced YOLOv8 architecture to enhance detection accuracy and efficiency for real-world objects and counting objects such as people, vehicles, and trees across various imaging modalities. The integration of high-resolution data from satellite systems offers a comprehensive view of both ground-level and aerial environments, supporting large-scale object detection and geospatial analysis. To address the limitations of conventional single-source models, the proposed dynamic model utilizes adaptive feature extraction and multi-scale learning strategies, which improve generalization across different resolutions and environmental conditions. Experimental results show that the model applies to two verified datasets that achieves superior performance in terms of detection precision and computational efficiency, confirming its potential for practical applications in urban monitoring, and environmental surveillance. This paper contributes to the advancement of Dual Dynamic Feature-based Deep Learning and Computer Vision\u0026ndash;Based AI Model to geospatial analytics by providing multi neural networks to identify multiple object types. The experimental accuracy results for multi object classification via two satellite imagery datasets achieve 99.9%.\u003c/p\u003e","manuscriptTitle":"A Dual Dynamic Feature-based Deep Learning and Computer Vision–Based Model for Multi-Object Classification Using Geospatial Satellite Imagery","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-03 18:04:02","doi":"10.21203/rs.3.rs-8992042/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":"bd8c9c3b-e2f9-4212-b146-d07f1957f43f","owner":[],"postedDate":"March 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-03T18:04:02+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-03 18:04:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8992042","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8992042","identity":"rs-8992042","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}