An Efficient Fire Detection Algorithm Based on Mamba Space State Linear Attention

An Efficient Fire Detection Algorithm Based on Mamba Space State Linear Attention | 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 An Efficient Fire Detection Algorithm Based on Mamba Space State Linear Attention Yuming Li, Yongjie Wang, Xiaorui Shao, Anbo Zheng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5986604/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract The Mamba model, as a State Space Model (SSM), enhances the global receptive field and feature extraction capabilities of object detection models through an architecture inspired by Recurrent Neural Networks (RNNs). Compared to traditional Convolutional Neural Networks (CNNs) and Transformers, it excels in handling complex scale variations and multi-view interference, offering a novel approach for object detection tasks in dynamic environments such as fire detection. Therefore, this paper proposes an efficient attention mechanism, the Efficient-Mamba-Attention (EMA) module, which enhances input features through adaptive average pooling and SSM modules. By integrating the EMA module with the YOLOv9 architecture, a highly efficient fire detection algorithm is proposed, particularly suitable for complex scenarios. Additionally, the model introduces the ConvNeXtV2 block to strengthen the backbone network, compensating for the limitations of SSM models in local feature modeling. Finally, the introduction of dynamic non-monotonic focusing and distance penalty mechanisms optimizes the loss function, improving the accuracy of the detection bounding boxes and significantly enhancing the precision and robustness of the fire alarm tasks. Comparative experiments demonstrate that the proposed network excels in terms of AP50 and FPS, achieving an AP50 of 91.0% on the large-scale fire dataset (dataset1), and 87.2% on the small-scale fire dataset (dataset2), with FPS reaching 71 on dataset1 and 64 on dataset2. This demonstrates that the proposed method maintains high detection performance while achieving outstanding efficiency. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Physical sciences/Optics and photonics/Optical techniques/Imaging and sensing Physical sciences/Mathematics and computing/Computational science Fire Detection Object Detection Computer Vision Mamba Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 21 Feb, 2025 Reviews received at journal 20 Feb, 2025 Reviews received at journal 13 Feb, 2025 Reviewers agreed at journal 12 Feb, 2025 Reviewers agreed at journal 12 Feb, 2025 Reviewers invited by journal 12 Feb, 2025 Editor assigned by journal 12 Feb, 2025 Editor invited by journal 10 Feb, 2025 Submission checks completed at journal 10 Feb, 2025 First submitted to journal 08 Feb, 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-5986604","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":413567085,"identity":"373a0e4f-859f-4f99-a963-b25ab5ebf5df","order_by":0,"name":"Yuming Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYBACNmbGxgcfftjwsLE3H2CQAAkdIKCFj7252XBmT5ocP8+xxAaitMjxHG+T5mE7bCw5w8ewgYEYLWwSic0GPDzMiRtu8Hx/YNnGIMd3I4HxcwF+LY0PJCzYEjfc7t3YINnGYCx5I4FZegYhW4DWJG64cxasBWhdAhszD34tbRIJQHLDjZyHIC31hLXwHGyTOMBmAPR+DiNIS4IBQS3sjc2GjT0JoEA2nCFxTsJw5pmHzdL4tMg3sz98/OfHf1BUPvgsUWYjz3c8+eBnfFpQALMEOP4ZG4jVAFT7gXi1o2AUjIJRMIIAADQ5TyF7UiOFAAAAAElFTkSuQmCC","orcid":"","institution":"Luoyang Polytechnic","correspondingAuthor":true,"prefix":"","firstName":"Yuming","middleName":"","lastName":"Li","suffix":""},{"id":413567086,"identity":"d44e56b2-d3c5-4236-b9b3-1d85468769bb","order_by":1,"name":"Yongjie Wang","email":"","orcid":"","institution":"Shijiazhuang Tiedao University","correspondingAuthor":false,"prefix":"","firstName":"Yongjie","middleName":"","lastName":"Wang","suffix":""},{"id":413567087,"identity":"b693cfa7-5482-49fb-aacc-54602cc75655","order_by":2,"name":"Xiaorui Shao","email":"","orcid":"","institution":"Luoyang Polytechnic","correspondingAuthor":false,"prefix":"","firstName":"Xiaorui","middleName":"","lastName":"Shao","suffix":""},{"id":413567088,"identity":"3135c127-00a0-43b1-a3bd-7f225e35ed1d","order_by":3,"name":"Anbo Zheng","email":"","orcid":"","institution":"Jiaxing Nanhu University","correspondingAuthor":false,"prefix":"","firstName":"Anbo","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2025-02-08 09:08:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5986604/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5986604/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-95162-z","type":"published","date":"2025-04-02T15:56:58+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80081961,"identity":"4d8d887c-1080-42fb-b497-24db3846ccae","added_by":"auto","created_at":"2025-04-07 16:03:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8695456,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5986604/v1_covered_bbaa47ad-f766-4a6f-91dd-eafa0d3eab35.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Efficient Fire Detection Algorithm Based on Mamba Space State Linear Attention","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Fire Detection, Object Detection, Computer Vision, Mamba","lastPublishedDoi":"10.21203/rs.3.rs-5986604/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5986604/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The Mamba model, as a State Space Model (SSM), enhances the global receptive field and feature extraction capabilities of object detection models through an architecture inspired by Recurrent Neural Networks (RNNs). Compared to traditional Convolutional Neural Networks (CNNs) and Transformers, it excels in handling complex scale variations and multi-view interference, offering a novel approach for object detection tasks in dynamic environments such as fire detection. Therefore, this paper proposes an efficient attention mechanism, the Efficient-Mamba-Attention (EMA) module, which enhances input features through adaptive average pooling and SSM modules. By integrating the EMA module with the YOLOv9 architecture, a highly efficient fire detection algorithm is proposed, particularly suitable for complex scenarios. Additionally, the model introduces the ConvNeXtV2 block to strengthen the backbone network, compensating for the limitations of SSM models in local feature modeling. Finally, the introduction of dynamic non-monotonic focusing and distance penalty mechanisms optimizes the loss function, improving the accuracy of the detection bounding boxes and significantly enhancing the precision and robustness of the fire alarm tasks. Comparative experiments demonstrate that the proposed network excels in terms of AP50 and FPS, achieving an AP50 of 91.0% on the large-scale fire dataset (dataset1), and 87.2% on the small-scale fire dataset (dataset2), with FPS reaching 71 on dataset1 and 64 on dataset2. This demonstrates that the proposed method maintains high detection performance while achieving outstanding efficiency.","manuscriptTitle":"An Efficient Fire Detection Algorithm Based on Mamba Space State Linear Attention","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-12 05:47:38","doi":"10.21203/rs.3.rs-5986604/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-02-21T10:29:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-21T03:37:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-14T03:42:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324282953271666330320478638633033408390","date":"2025-02-13T03:03:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62098894549797738476621933981272029788","date":"2025-02-13T02:51:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-02-13T02:38:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-02-13T02:14:06+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-02-10T10:23:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-02-10T09:23:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-02-08T09:04:28+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"868b54da-181e-4c8e-901f-e0ca779a3faf","owner":[],"postedDate":"February 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":44096761,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":44096762,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":44096763,"name":"Physical sciences/Optics and photonics/Optical techniques/Imaging and sensing"},{"id":44096764,"name":"Physical sciences/Mathematics and computing/Computational science"}],"tags":[],"updatedAt":"2025-04-07T15:58:35+00:00","versionOfRecord":{"articleIdentity":"rs-5986604","link":"https://doi.org/10.1038/s41598-025-95162-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-04-02 15:56:58","publishedOnDateReadable":"April 2nd, 2025"},"versionCreatedAt":"2025-02-12 05:47:38","video":"","vorDoi":"10.1038/s41598-025-95162-z","vorDoiUrl":"https://doi.org/10.1038/s41598-025-95162-z","workflowStages":[]},"version":"v1","identity":"rs-5986604","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5986604","identity":"rs-5986604","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}