Simplified LSL-Net architecture for Unmanned Aerial Vehicles detection in real-time | 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 Simplified LSL-Net architecture for Unmanned Aerial Vehicles detection in real-time Francisco David Camacho-Gonzalez, Nestor Andres Garcia-Rojas, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5314628/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Apr, 2025 Read the published version in Technologies → Version 1 posted You are reading this latest preprint version Abstract In this paper, we propose a simplified architecture based on LSL-Net for detecting unmanned aerial vehicles, this architecture integrates the ability to track and detect them, based on convolutional neural networks. The biggest challenge is the creation of a model that allows us to have good results without the need for large computational resources, in addition to this we must take into account the scarcity of training images for drone detection. To address this problem, we developed simplified LSL-Net architecture using dilated convolutions that allows us to reach our objective. Finally, our proposed architecture integrates the detection and tracking of drones. Experiments show that our architecture performs well with limited resources, achieving an accuracy of 97% in training and in the detection of new elements. Object detection UAV Dilated convolutions low-attitude Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 30 Apr, 2025 Read the published version in Technologies → 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-5314628","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":369654683,"identity":"e1a739c7-a6e0-4145-8cb6-71c77f099da5","order_by":0,"name":"Francisco David Camacho-Gonzalez","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFklEQVRIiWNgGAWjYBAC9gYQaYAQSGBgb2zAq4XnAIYWnoPEaEECCQwSCfgdxiN9+NmDHwV18vwMzA8/3aixy+OXfNz24EeFTR6D2BkDrFr40swNewwOG85sYDOWzjmWXCw5O7HdsOdMWjGDdBpW++x5GMykGQwOJBgc4GGQzmE7kLjhdmKbBG/b4cQG6WR0V0Ns4WH/BtRSB9LC/DvnH1DLzYNtkn/b/gO1JGINBx4eHpAtzCAtbNK5bUAtNxjbpHmBDNy28JRJgv3SzGZmnduXnDizJ7FNWuZMcjEbDr8AHbZN4scfYIixNz++nfPNLrGf/fgzyTcVwKCTzsEaYgjAjMZPYMOvHgvA6qhRMApGwSgYkQAAer5aVxeafFEAAAAASUVORK5CYII=","orcid":"","institution":"National Institute of Astrophysics, Optics and Electronics","correspondingAuthor":true,"prefix":"","firstName":"Francisco","middleName":"David","lastName":"Camacho-Gonzalez","suffix":""},{"id":369654684,"identity":"3c563cc2-9bde-4fcf-a7cc-b02ac1bbb461","order_by":1,"name":"Nestor Andres Garcia-Rojas","email":"","orcid":"","institution":"National Institute of Astrophysics, Optics and Electronics","correspondingAuthor":false,"prefix":"","firstName":"Nestor","middleName":"Andres","lastName":"Garcia-Rojas","suffix":""},{"id":369654685,"identity":"d6469f92-704d-4220-9903-ae37cdc86c1f","order_by":2,"name":"José Francisco Martínez-Trinidad","email":"","orcid":"","institution":"National Institute of Astrophysics, Optics and Electronics","correspondingAuthor":false,"prefix":"","firstName":"José","middleName":"Francisco","lastName":"Martínez-Trinidad","suffix":""},{"id":369654686,"identity":"106bc4ab-7b55-44aa-a695-eb4583fd9d34","order_by":3,"name":"Jesús Ariel Carrasco-Ochoa","email":"","orcid":"","institution":"National Institute of Astrophysics, Optics and Electronics","correspondingAuthor":false,"prefix":"","firstName":"Jesús","middleName":"Ariel","lastName":"Carrasco-Ochoa","suffix":""}],"badges":[],"createdAt":"2024-10-23 00:08:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5314628/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5314628/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.3390/technologies13050177","type":"published","date":"2025-05-01T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":82076870,"identity":"7d636431-ff7e-4616-864a-f761e3b7a657","added_by":"auto","created_at":"2025-05-06 13:57:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":710776,"visible":true,"origin":"","legend":"","description":"","filename":"SimplifiedLSLNetarchitectureforUnmannedAerialVehiclesdetectioninrealtime.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5314628/v1_covered_b64c9b62-ebfc-4eb5-9eac-661cc4ff056a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Simplified LSL-Net architecture for Unmanned Aerial Vehicles detection in real-time","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":"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":"Object detection, UAV, Dilated convolutions, low-attitude","lastPublishedDoi":"10.21203/rs.3.rs-5314628/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5314628/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In this paper, we propose a simplified architecture based on LSL-Net for detecting unmanned aerial vehicles, this architecture integrates the ability to track and detect them, based on convolutional neural networks. The biggest challenge is the creation of a model that allows us to have good results without the need for large computational resources, in addition to this we must take into account the scarcity of training images for drone detection. To address this problem, we developed simplified LSL-Net architecture using dilated convolutions that allows us to reach our objective. Finally, our proposed architecture integrates the detection and tracking of drones. Experiments show that our architecture performs well with limited resources, achieving an accuracy of 97\\% in training and in the detection of new elements.","manuscriptTitle":"Simplified LSL-Net architecture for Unmanned Aerial Vehicles detection in real-time","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-25 12:42:50","doi":"10.21203/rs.3.rs-5314628/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":"32ad5ed9-9e6d-4119-b115-b65214397093","owner":[],"postedDate":"October 25th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-05-06T13:57:04+00:00","versionOfRecord":{"articleIdentity":"rs-5314628","link":"https://doi.org/10.3390/technologies13050177","journal":{"identity":"technologies","isVorOnly":true,"title":"Technologies"},"publishedOn":"2025-05-01 00:00:00","publishedOnDateReadable":"May 1st, 2025"},"versionCreatedAt":"2024-10-25 12:42:50","video":"","vorDoi":"10.3390/technologies13050177","vorDoiUrl":"https://doi.org/10.3390/technologies13050177","workflowStages":[]},"version":"v1","identity":"rs-5314628","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5314628","identity":"rs-5314628","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","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.