EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection

EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection | 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 EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection Dongmei Wang, Ying Qian, Jingyi Lu, Peng Wang, Dandi Yang, Tianhong Yan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3930713/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 For fire detection, there are characteristics such as variable sample feature morphology, complex background and dense target, small sample size of dataset and imbalance ofcategories, which lead to the problems of low accuracy and poor real-time performanceof the existing fire detection models. We propose a flame smoke detection model basedon efficient multi-scale feature enhancement, i.e., EA-YOLO. In order to improve theextraction capability of the network model for flame target features, an efficient attentionmechanism is integrated into the backbone network, Multi Channel Attention (MCA), andthe number of parameters of the model is reduced by introducing the RepVB module;at the same time, we design a multi-weighted multidirectional feature neck structure,Multidirectional Feature Pyramid Network (MDFPN), to enhance the model’s flametarget feature information fusion ability; finally, the CIoU loss function is redesigned byintroducing the Slide weighting function to improve the imbalance between difficult andeasy samples. In addition, to address the problem of a small sample size of fire datasets,this paper establishes two fire datasets, Fire-Smoke and Ro-Fire-Smoke, of which thelatter has the model robustness validation function. The experimental results show that themethod of this paper is 6.5% and 7.3% higher compared to the baseline model YOLOv7on the Fire-Smoke and Ro-Fire-Smoke datasets, respectively. The detection speed is 74.6frames per second. It fully demonstrates that the method in this paper has high flamedetection accuracy while considering the real-time nature of the model. The source codeand dataset are located at https://github.com/DIADH/DIADH.YOLO. Fire detection EA-YOLO Attention mechanisms Feature extraction and fusion Fire datasets Full Text Additional Declarations No competing interests reported. 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-3930713","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":271404615,"identity":"67314863-6ef1-414b-b19c-2acc06a986ae","order_by":0,"name":"Dongmei Wang","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Dongmei","middleName":"","lastName":"Wang","suffix":""},{"id":271404616,"identity":"dca44e9e-9f53-4279-a4ce-2fc383572e26","order_by":1,"name":"Ying Qian","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Qian","suffix":""},{"id":271404617,"identity":"19bbf46f-e770-4a9a-a737-4b1f92b06e67","order_by":2,"name":"Jingyi Lu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqklEQVRIiWNgGAWjYBACPoYDDAw8DDY8/OwNRGphg2hJk5HsOUC0FgaQlsM2BjcciNXCeMZM4m3OeR6GGwyMHz7mEGXLGTPJudtu8zDObmCWnLmNSC23eYFamGUOsDHzkqDlHA+bRAJpWg7w8JCg5Vj5z7nbknkkeA42E+cXfonDmw3ebrOztz/efPDDR2K0MEicMICyGBuIUQ+ypv0BkSpHwSgYBaNgxAIA9+M0jwUM7SYAAAAASUVORK5CYII=","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":true,"prefix":"","firstName":"Jingyi","middleName":"","lastName":"Lu","suffix":""},{"id":271404618,"identity":"1dfff41f-bae0-4769-8f19-7dfc14548653","order_by":3,"name":"Peng Wang","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Wang","suffix":""},{"id":271404619,"identity":"3e8884d7-bcf9-4b9e-8a36-33c209c14df7","order_by":4,"name":"Dandi Yang","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Dandi","middleName":"","lastName":"Yang","suffix":""},{"id":271404623,"identity":"4a537d85-8b99-4b67-9776-77fa8a15dd87","order_by":5,"name":"Tianhong Yan","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Tianhong","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2024-02-05 11:03:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3930713/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3930713/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":50867809,"identity":"00a4a9e1-c785-4aa4-a7d1-9b99675471bf","added_by":"auto","created_at":"2024-02-08 15:55:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1566456,"visible":true,"origin":"","legend":"","description":"","filename":"sntemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3930713/v1_covered_aa005b37-eca9-45b7-9750-c11ed5258adf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection","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":"Fire detection, EA-YOLO, Attention mechanisms, Feature extraction and fusion, Fire datasets","lastPublishedDoi":"10.21203/rs.3.rs-3930713/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3930713/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFor fire detection, there are characteristics such as variable sample feature morphology, complex background and dense target, small sample size of dataset and imbalance ofcategories, which lead to the problems of low accuracy and poor real-time performanceof the existing fire detection models. We propose a flame smoke detection model basedon efficient multi-scale feature enhancement, i.e., EA-YOLO. In order to improve theextraction capability of the network model for flame target features, an efficient attentionmechanism is integrated into the backbone network, Multi Channel Attention (MCA), andthe number of parameters of the model is reduced by introducing the RepVB module;at the same time, we design a multi-weighted multidirectional feature neck structure,Multidirectional Feature Pyramid Network (MDFPN), to enhance the model’s flametarget feature information fusion ability; finally, the CIoU loss function is redesigned byintroducing the Slide weighting function to improve the imbalance between difficult andeasy samples. In addition, to address the problem of a small sample size of fire datasets,this paper establishes two fire datasets, Fire-Smoke and Ro-Fire-Smoke, of which thelatter has the model robustness validation function. The experimental results show that themethod of this paper is 6.5% and 7.3% higher compared to the baseline model YOLOv7on the Fire-Smoke and Ro-Fire-Smoke datasets, respectively. The detection speed is 74.6frames per second. It fully demonstrates that the method in this paper has high flamedetection accuracy while considering the real-time nature of the model. The source codeand dataset are located at https://github.com/DIADH/DIADH.YOLO.\u003c/p\u003e","manuscriptTitle":"EA-YOLO: Efficient Extraction and Aggregation Mechanismof YOLO for Fire Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-08 06:38:58","doi":"10.21203/rs.3.rs-3930713/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":"cc65b35f-90df-4bde-9721-4799e5ccde41","owner":[],"postedDate":"February 8th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-02-08T15:47:30+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-08 06:38:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3930713","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3930713","identity":"rs-3930713","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}