Multiscale Feature Optimization for Accurate Small Object Detection in Remote Sensing Imagery

Multiscale Feature Optimization for Accurate Small Object Detection in Remote Sensing 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 Multiscale Feature Optimization for Accurate Small Object Detection in Remote Sensing Imagery Bingxiang Wang, Mugen Zhou, Wenzhuo Ma, Tianyu Li, Changsheng Zhu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9124242/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 11 You are reading this latest preprint version Abstract Detecting small, overlapping objects in high-resolution remote sensing imagery is crucial for applications such as smart city monitoring and disaster response. However, challenges such as severe feature confusion and spatial misalignment hinder accurate localization. This paper introduces Multiscale SOG-DETR, a systematic redesign of the RT-DETR framework tailored for remote sensing small-object detection. We propose a lightweight Multiscale Overlapping-Object Decoupling Network (MOODNet) to significantly reduce feature entanglement in overlapping regions. Additionally, our specialized fusion neck, comprising the Residual Spatial-Alignment Progressive Fusion Module (SAPFM), E-CGAFusion, and WTConv2d modules, enhances multiscale semantic focus and preserves high-frequency details cost-effectively. Experimental results on the RSOD, VisDrone2019, and NWPU VHR-10 datasets demonstrate that Multiscale SOG-DETR achieves superior detection accuracy with significantly fewer parameters compared to the baseline RT-DETR model, increasing AP_ IoU=50 by 3.1%, 3.0%, and 5.2%, and AP IoU=50:95 by 5.1%, 2.1%, and 8.5%, respectively. These findings position Multiscale SOG-DETR as a promising solution for efficient and accurate small-object detection in remote sensing applications.The source code is publicly available at https://github.com/AaronWang-code/Multiscale-SOG-DETR. Remote sensing imagery overlapping objects MOODNet E-CGAFusion SAPFM Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 24 Apr, 2026 Reviews received at journal 24 Apr, 2026 Reviews received at journal 15 Apr, 2026 Reviewers agreed at journal 15 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviewers agreed at journal 13 Apr, 2026 Reviewers agreed at journal 13 Apr, 2026 Reviewers invited by journal 13 Apr, 2026 Editor assigned by journal 16 Mar, 2026 Submission checks completed at journal 16 Mar, 2026 First submitted to journal 14 Mar, 2026 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-9124242","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":623374472,"identity":"1975b283-3572-489c-b2fd-ab9bb2c68468","order_by":0,"name":"Bingxiang Wang","email":"","orcid":"","institution":"Xi'an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Bingxiang","middleName":"","lastName":"Wang","suffix":""},{"id":623374473,"identity":"7922b68f-7618-46ab-b303-5eb5513593e4","order_by":1,"name":"Mugen Zhou","email":"","orcid":"","institution":"Xi'an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Mugen","middleName":"","lastName":"Zhou","suffix":""},{"id":623374474,"identity":"1366e68f-db48-40b6-bfd4-bfd24a420bfb","order_by":2,"name":"Wenzhuo Ma","email":"","orcid":"","institution":"Xi'an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Wenzhuo","middleName":"","lastName":"Ma","suffix":""},{"id":623374475,"identity":"c92171b3-5179-4706-8b5f-ba017318b37a","order_by":3,"name":"Tianyu Li","email":"","orcid":"","institution":"Lanzhou University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tianyu","middleName":"","lastName":"Li","suffix":""},{"id":623374476,"identity":"1eaac933-1e69-4b9a-9d06-cfbf747c02cf","order_by":4,"name":"Changsheng Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYDACCTBpw8PG3nzgwIcfxGtJk+PnOZZ4cGYP8VoOG0vOyDE+zMFGhA752T2GH38wMCduOHPmw2EGHgZ5frED+LUwzjljLM3DwJa44XjvhsMFFgyGM2cn4NfCLJFjxszAwAO05eyGwzN4GBIMbhPQwgbUwviDQSJxw42cB4d52IjQwgPUAvSBAcj7DMRpkZBIKwb6JQEUyAbAQJYg7Bf5GckbgSH2HxSVjz98+GEjzy9NQAsYMP5D2EqE8lEwCkbBKBgFBAEAK/BBofvMFJwAAAAASUVORK5CYII=","orcid":"","institution":"Lanzhou University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Changsheng","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2026-03-14 17:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9124242/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9124242/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107483104,"identity":"2009165d-7f26-45a1-9c8b-b0073b83161c","added_by":"auto","created_at":"2026-04-22 02:26:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2027187,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9124242/v1_covered_d5444024-8cfd-49bf-b711-e85028a84f83.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multiscale Feature Optimization for Accurate Small Object Detection in Remote Sensing Imagery","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Remote sensing imagery, overlapping objects, MOODNet, E-CGAFusion, SAPFM","lastPublishedDoi":"10.21203/rs.3.rs-9124242/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9124242/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDetecting small, overlapping objects in high-resolution remote sensing imagery is crucial for applications such as smart city monitoring and disaster response. However, challenges such as severe feature confusion and spatial misalignment hinder accurate localization. This paper introduces Multiscale SOG-DETR, a systematic redesign of the RT-DETR framework tailored for remote sensing small-object detection. We propose a lightweight Multiscale Overlapping-Object Decoupling Network (MOODNet) to significantly reduce feature entanglement in overlapping regions. Additionally, our specialized fusion neck, comprising the Residual Spatial-Alignment Progressive Fusion Module (SAPFM), E-CGAFusion, and WTConv2d modules, enhances multiscale semantic focus and preserves high-frequency details cost-effectively. Experimental results on the RSOD, VisDrone2019, and NWPU VHR-10 datasets demonstrate that Multiscale SOG-DETR achieves superior detection accuracy with significantly fewer parameters compared to the baseline RT-DETR model, increasing \u003cem\u003e\u003cstrong\u003eAP_\u003c/strong\u003e\u003c/em\u003e\u003csub\u003e\u003cem\u003e\u003cstrong\u003eIoU=50\u003c/strong\u003e\u003c/em\u003e\u003c/sub\u003e by 3.1%, 3.0%, and 5.2%, and \u003cem\u003e\u003cstrong\u003eAP\u003c/strong\u003e\u003c/em\u003e\u003csub\u003e\u003cem\u003e\u003cstrong\u003eIoU=50:95\u003c/strong\u003e\u003c/em\u003e\u003c/sub\u003e by 5.1%, 2.1%, and 8.5%, respectively. These findings position Multiscale SOG-DETR as a promising solution for efficient and accurate small-object detection in remote sensing applications.The source code is publicly available at https://github.com/AaronWang-code/Multiscale-SOG-DETR.\u003c/p\u003e","manuscriptTitle":"Multiscale Feature Optimization for Accurate Small Object Detection in Remote Sensing Imagery","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 18:04:41","doi":"10.21203/rs.3.rs-9124242/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-24T08:25:46+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-24T06:21:48+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T06:13:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"5475191745438597125047629161849023358","date":"2026-04-15T06:07:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-14T03:56:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"30963692805028968412805122976081925945","date":"2026-04-13T11:56:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"228445838059513593541365627346013168272","date":"2026-04-13T06:23:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-13T05:27:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-16T05:32:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-16T05:31:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2026-03-14T17:25:22+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"16634958-a397-41ef-9ae7-da0826246d03","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T08:39:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 18:04:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9124242","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9124242","identity":"rs-9124242","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}