Improved Flame Detection Based on Global Attention Mechanism and Deformable Convolution

Improved Flame Detection Based on Global Attention Mechanism and Deformable Convolution | 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 Article Improved Flame Detection Based on Global Attention Mechanism and Deformable Convolution Wen Ni, Lufeng Bai This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6494403/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 conducts a more thorough research and discussion on the detection of flame and smoke objects. To achieve real-time and accurate monitoring of smoke and fire targets in fire scenarios, the Improve-YOLOv8 algorithm is proposed based on YOLOv8. Firstly, this model replaces the C2f module with the DCNv2 module at the Backbone end, which can adaptively adjust according to the proportion and morphology of the flame and smoke targets. This design effectively addresses the issue of insufficient sampling of the fixed rectangular structure, thereby enhancing the models accuracy. Secondly, a small object detection layer is added in the Head part to address the challenge of accurately recognizing small flame targets. Additionally, the GAM attention mechanism is integrated after the Backbone SPPF module to further improve the accuracy and focus of image processing, thereby enhancing the overall processing efficiency. Finally, migration learning is implemented using sample data to effectively differentiate flame and smoke information and enhance detection accuracy. The experimental results show that the accuracy of the improved algorithm model reaches 98.6%, and the accuracy is improved by 10.5% compared with the original YOLOv8n, and mAP @0.5 9.6%. The comprehensive performance is improved, and the model can realize the real-time monitoring and accurate identification of fire and smoke. Earth and environmental sciences/Environmental sciences Earth and environmental sciences/Environmental social sciences Physical sciences/Energy science and technology Physical sciences/Mathematics and computing small target detection layer Improved-YOLOv8 GAM attention mechanism Full Text Additional Declarations No competing interests reported. Supplementary Files texFlame.zip 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-6494403","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":457304550,"identity":"52146da8-a586-48ee-8745-10d0682202c5","order_by":0,"name":"Wen Ni","email":"","orcid":"","institution":"University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Ni","suffix":""},{"id":457304551,"identity":"0e00a240-ee88-4a26-b431-08b935ffb5c4","order_by":1,"name":"Lufeng Bai","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYBACAwbGxgMMNkAWM/MBA7ggAS0NBxjSgCx2tgRitTAwQLTw8xggC+IG5uyHGw7zJNjkyTvzfCj88edOYgN78zYJhpo7OLVY9iSCtKQVGx7m3WDM2/YssYHnWJkEw7FnuB12AKiF98fhxI3NQC2MDYcTGyRyzCSADNxazj8E2fIfqIXngeGPP0At8m8IaLkBdtiBxPnMPAwGPGwgW3jwa7Gc8bDh4JyE5MQNzGwGQL8cNm7jSSu2SDiGW4s5f/rDB28S7BLn9x9+BnKYbD/74Y03PtTg1oIUDgxs4PhgAxEJhDUwMMg3MDA/IEbhKBgFo2AUjDwAAOdMXBhHKiMgAAAAAElFTkSuQmCC","orcid":"","institution":"Jiangsu Second Normal University","correspondingAuthor":true,"prefix":"","firstName":"Lufeng","middleName":"","lastName":"Bai","suffix":""}],"badges":[],"createdAt":"2025-04-21 09:08:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6494403/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6494403/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90636481,"identity":"8dad5789-5f94-4e44-b8d8-90e4c855d816","added_by":"auto","created_at":"2025-09-05 05:02:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1822817,"visible":true,"origin":"","legend":"","description":"","filename":"flamedetect25421.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6494403/v1_covered_570c45c1-1cbd-49a6-819b-72e0575a7a32.pdf"},{"id":82905913,"identity":"900a9ee9-3444-412e-980a-33a81cd76746","added_by":"auto","created_at":"2025-05-16 14:15:44","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":13835267,"visible":true,"origin":"","legend":"","description":"","filename":"texFlame.zip","url":"https://assets-eu.researchsquare.com/files/rs-6494403/v1/84a8d5d31105711ea8bb6e7d.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improved Flame Detection Based on Global Attention Mechanism and Deformable Convolution","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"small target detection layer, Improved-YOLOv8, GAM attention mechanism","lastPublishedDoi":"10.21203/rs.3.rs-6494403/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6494403/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper conducts a more thorough research and discussion on the detection of flame and smoke objects. To achieve real-time and accurate monitoring of smoke and fire targets in fire scenarios, the Improve-YOLOv8 algorithm is proposed based on YOLOv8. Firstly, this model replaces the C2f module with the DCNv2 module at the Backbone end, which can adaptively adjust according to the proportion and morphology of the flame and smoke targets. This design effectively addresses the issue of insufficient sampling of the fixed rectangular structure, thereby enhancing the models accuracy. Secondly, a small object detection layer is added in the Head part to address the challenge of accurately recognizing small flame targets. Additionally, the GAM attention mechanism is integrated after the Backbone SPPF module to further improve the accuracy and focus of image processing, thereby enhancing the overall processing efficiency. Finally, migration learning is implemented using sample data to effectively differentiate flame and smoke information and enhance detection accuracy. The experimental results show that the accuracy of the improved algorithm model reaches 98.6%, and the accuracy is improved by 10.5% compared with the original YOLOv8n, and mAP @0.5 9.6%. The comprehensive performance is improved, and the model can realize the real-time monitoring and accurate identification of fire and smoke.","manuscriptTitle":"Improved Flame Detection Based on Global Attention Mechanism and Deformable Convolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-16 14:15:39","doi":"10.21203/rs.3.rs-6494403/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":"70161c42-cbc6-4092-b085-3abe16af95c4","owner":[],"postedDate":"May 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48604217,"name":"Earth and environmental sciences/Environmental sciences"},{"id":48604218,"name":"Earth and environmental sciences/Environmental social sciences"},{"id":48604219,"name":"Physical sciences/Energy science and technology"},{"id":48604220,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-09-05T04:53:57+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-16 14:15:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6494403","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6494403","identity":"rs-6494403","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}