RS-LMF2 : Refined Sparse with Large Receptive field and Multi-Scale Feature Fusion for Remote Sensing Object Detection

RS-LMF2 : Refined Sparse with Large Receptive field and Multi-Scale Feature Fusion for Remote Sensing Object Detection | 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 RS-LMF 2 : Refined Sparse with Large Receptive field and Multi-Scale Feature Fusion for Remote Sensing Object Detection Yanbo Che This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4749397/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 Remote sensing images object detection as a research hots-pot in recent years, its detection effect and inference speed are attracting much attention. Small receptive field often lead to object classification errors because of the similarity features between different categories. In addition, the large size of remote sensing images leads to slow inference speed. To address above problems, this paper proposes a single-stage rotated object detector RS-LMF 2 . Firstly, ResNet-Dil module is used to increase the receiver field of the model, and then the Augment-FPN module is used to merge the feature information between the bottom layer and the top layer to obtain prior knowledge, so that the model can capture enough background information in the remote sensing objects to increase the detection effect of the model. In order to improve inference speed, this paper designs the refined sparse module, which not only reduces the number of initial settings of anchor, but also uses multiple convolutions to obtain the angle information of the objects, so that the horizontal box is gradually regressed into a rotated box to improve the inference speed. RS-LMF 2 achieves excellent results in two datasets, i.e., DOTA (79.0% mAP, 22.3 FPS), and UCAS-AOD (90.8% mAP, 39.2 FPS) on an NVIDIA 3090 GPU. Remote Sensing Oriented object detection Prior knowledge 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-4749397","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":328221825,"identity":"2b4c770c-fdf0-4347-bc18-52da7eed1232","order_by":0,"name":"Yanbo Che","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIie3PsUvDQBTH8VcOrg4Ps16xpP/CyUEc/VfeEeikohTKDR2ElrvBdO+fIXTpmCxxOeuaMf0PFJdsbXcliZvDfeb3hd8DCIJ/iE8+atWYYxwNXVGTWXQnlwJhBp6pUeZTWfuyO4nPyffAMi0rSkaHFesx7GpdbJ8sJ6hoavQzh8i9UHsy3qdqs8eHQXYoK70bg/Dvr+0JUCJxLmZsSNNKew5S3HcmNw1yqe25fdSW9UjEnVRoSWcXlEC/BEu63vhcCfSpIF9i5y8Tt8zlp8nj2zdXfDVmEUdu3Z78gH87D4IgCH51At21TH63/UBhAAAAAElFTkSuQmCC","orcid":"","institution":"Heilongjiang University","correspondingAuthor":true,"prefix":"","firstName":"Yanbo","middleName":"","lastName":"Che","suffix":""}],"badges":[],"createdAt":"2024-07-16 11:38:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4749397/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4749397/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60545716,"identity":"b5572ae6-a03e-4671-b370-65a3758290e3","added_by":"auto","created_at":"2024-07-18 03:41:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1242380,"visible":true,"origin":"","legend":"","description":"","filename":"RSLMF2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4749397/v1_covered_ba1d742e-05b1-444c-b273-9e407c795888.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eRS-LMF\u003csup\u003e2\u003c/sup\u003e : Refined Sparse with Large Receptive field and Multi-Scale Feature Fusion for Remote Sensing Object Detection\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":"Remote Sensing, Oriented object detection, Prior knowledge","lastPublishedDoi":"10.21203/rs.3.rs-4749397/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4749397/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRemote sensing images object detection as a research hots-pot in recent years, its detection effect and inference speed are attracting much attention. Small receptive field often lead to object classification errors because of the similarity features between different categories. In addition, the large size of remote sensing images leads to slow inference speed. To address above problems, this paper proposes a single-stage rotated object detector RS-LMF\u003csup\u003e2\u003c/sup\u003e. Firstly, ResNet-Dil module is used to increase the receiver field of the model, and then the Augment-FPN module is used to merge the feature information between the bottom layer and the top layer to obtain prior knowledge, so that the model can capture enough background information in the remote sensing objects to increase the detection effect of the model. In order to improve inference speed, this paper designs the refined sparse module, which not only reduces the number of initial settings of anchor, but also uses multiple convolutions to obtain the angle information of the objects, so that the horizontal box is gradually regressed into a rotated box to improve the inference speed. RS-LMF\u003csup\u003e2\u003c/sup\u003e achieves excellent results in two datasets, i.e., DOTA (79.0% mAP, 22.3 FPS), and UCAS-AOD (90.8% mAP, 39.2 FPS) on an NVIDIA 3090 GPU.\u003c/p\u003e","manuscriptTitle":"RS-LMF2 : Refined Sparse with Large Receptive field and Multi-Scale Feature Fusion for Remote Sensing Object Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-18 03:33:15","doi":"10.21203/rs.3.rs-4749397/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":"1b3b3ca5-ad5a-4eff-95d5-57a87cb747cf","owner":[],"postedDate":"July 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-08-13T15:00:33+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-18 03:33:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4749397","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4749397","identity":"rs-4749397","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}