Advancing Multi-Class Object Detection from LEO/VLEO: Model Evaluation and Onboard Deployment tailored for a 16U CubeSat | 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 Advancing Multi-Class Object Detection from LEO/VLEO: Model Evaluation and Onboard Deployment tailored for a 16U CubeSat Bharadwaj Chintalapati, Aras Jafari, Rene Laufer, Marcus Liwicki, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6555469/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Jan, 2026 Read the published version in CEAS Space Journal → Version 1 posted 10 You are reading this latest preprint version Abstract On-board AI-based image recognition for Very Low Earth Orbit (VLEO) and Low Earth Orbit (LEO) missions enables the potential for high-resolution Earth Observation while minimizing data transmission needs. This paper presents a multi-class object detection approach using deep learning models. A custom Earth Observation dataset was created, considering orbital and sensor characteristics, to evaluate the model’s performance. This work provides proof of concept for real-time object detection in LEO/VLEO missions including deployment on to the based target edge hardware, addressing the challenges of limited computational resources and the need for automated image analysis. These results highlight the potential for autonomous payload operations for Earth Observation in future VLEO and LEO missions. VLEO CubeSat Earth Observation EO-Dataset Payload Operations Deep Learning Object Detection Edge Deployment Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Jan, 2026 Read the published version in CEAS Space Journal → Version 1 posted Editorial decision: Revision requested 06 Aug, 2025 Reviews received at journal 17 Jul, 2025 Reviews received at journal 20 Jun, 2025 Reviewers agreed at journal 30 May, 2025 Reviewers agreed at journal 25 May, 2025 Reviewers agreed at journal 11 May, 2025 Reviewers invited by journal 09 May, 2025 Editor assigned by journal 30 Apr, 2025 Submission checks completed at journal 29 Apr, 2025 First submitted to journal 29 Apr, 2025 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-6555469","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":454884290,"identity":"5657826f-4abf-4bc7-b8b8-35aad89f5cfa","order_by":0,"name":"Bharadwaj Chintalapati","email":"data:image/png;base64,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","orcid":"","institution":"Luleå University of Technology, LULEÅ","correspondingAuthor":true,"prefix":"","firstName":"Bharadwaj","middleName":"","lastName":"Chintalapati","suffix":""},{"id":454884291,"identity":"0c49f0d2-dc71-4215-9875-8d41c6bd9778","order_by":1,"name":"Aras Jafari","email":"","orcid":"","institution":"Luleå University of Technology, LULEÅ","correspondingAuthor":false,"prefix":"","firstName":"Aras","middleName":"","lastName":"Jafari","suffix":""},{"id":454884292,"identity":"f4b293b3-5153-46ca-a981-bec72fb0c76c","order_by":2,"name":"Rene Laufer","email":"","orcid":"","institution":"Luleå University of Technology, LULEÅ","correspondingAuthor":false,"prefix":"","firstName":"Rene","middleName":"","lastName":"Laufer","suffix":""},{"id":454884293,"identity":"8eb622f8-27d2-4919-948d-a6ebfc63b190","order_by":3,"name":"Marcus Liwicki","email":"","orcid":"","institution":"Luleå University of Technology, LULEÅ","correspondingAuthor":false,"prefix":"","firstName":"Marcus","middleName":"","lastName":"Liwicki","suffix":""},{"id":454884294,"identity":"6c306ddf-1a69-4e33-94e0-f2dded64f33e","order_by":4,"name":"Jens Eickhoff","email":"","orcid":"","institution":"Airbus Defence and Space GmbH","correspondingAuthor":false,"prefix":"","firstName":"Jens","middleName":"","lastName":"Eickhoff","suffix":""}],"badges":[],"createdAt":"2025-04-29 10:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6555469/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6555469/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s12567-025-00697-6","type":"published","date":"2026-01-27T15:59:21+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":101690578,"identity":"c427266c-1963-447c-bf85-39bd954a6e94","added_by":"auto","created_at":"2026-02-02 16:05:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2657472,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerChintalapati2025manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6555469/v1_covered_e0a8f325-626c-40c8-8d6d-b62f9d9ae999.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Advancing Multi-Class Object Detection from LEO/VLEO: Model Evaluation and Onboard Deployment tailored for a 16U CubeSat","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"ceas-space-journal","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ceas","sideBox":"Learn more about [CEAS Space Journal](http://link.springer.com/journal/12567)","snPcode":"12567","submissionUrl":"https://submission.nature.com/new-submission/12567/3","title":"CEAS Space Journal","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"VLEO, CubeSat, Earth Observation, EO-Dataset, Payload Operations, Deep Learning, Object Detection, Edge Deployment","lastPublishedDoi":"10.21203/rs.3.rs-6555469/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6555469/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOn-board AI-based image recognition for Very Low Earth Orbit (VLEO) and Low Earth Orbit (LEO) missions enables the potential for high-resolution Earth Observation while minimizing data transmission needs. This paper presents a multi-class object detection approach using deep learning models. A custom Earth Observation dataset was created, considering orbital and sensor characteristics, to evaluate the model\u0026rsquo;s performance. This work provides proof of concept for real-time object detection in LEO/VLEO missions including deployment on to the based target edge hardware, addressing the challenges of limited computational resources and the need for automated image analysis. These results highlight the potential for autonomous payload operations for Earth Observation in future VLEO and LEO missions.\u003c/p\u003e","manuscriptTitle":"Advancing Multi-Class Object Detection from LEO/VLEO: Model Evaluation and Onboard Deployment tailored for a 16U CubeSat","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-15 06:04:41","doi":"10.21203/rs.3.rs-6555469/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-06T05:29:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-17T13:16:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-20T20:56:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"157111659551457762251423716318579567656","date":"2025-05-30T08:32:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"164977393258794123627018267420132390610","date":"2025-05-25T16:05:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23516066663382376648505282196753698459","date":"2025-05-11T12:44:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-09T08:58:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-04-30T09:02:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-29T12:28:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"CEAS Space Journal","date":"2025-04-29T10:24:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"ceas-space-journal","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ceas","sideBox":"Learn more about [CEAS Space Journal](http://link.springer.com/journal/12567)","snPcode":"12567","submissionUrl":"https://submission.nature.com/new-submission/12567/3","title":"CEAS Space Journal","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"38f01970-33e8-4c99-9f42-cb7ac8f92a73","owner":[],"postedDate":"May 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-02T16:02:14+00:00","versionOfRecord":{"articleIdentity":"rs-6555469","link":"https://doi.org/10.1007/s12567-025-00697-6","journal":{"identity":"ceas-space-journal","isVorOnly":false,"title":"CEAS Space Journal"},"publishedOn":"2026-01-27 15:59:21","publishedOnDateReadable":"January 27th, 2026"},"versionCreatedAt":"2025-05-15 06:04:41","video":"","vorDoi":"10.1007/s12567-025-00697-6","vorDoiUrl":"https://doi.org/10.1007/s12567-025-00697-6","workflowStages":[]},"version":"v1","identity":"rs-6555469","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6555469","identity":"rs-6555469","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.