Pedestrian detection based on improved EfficientDet

Pedestrian detection based on improved EfficientDet | 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 Pedestrian detection based on improved EfficientDet Chengpeng Zhang, Miao Yu, Jian Min, Min Fu, Bing Zheng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3611172/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 Pedestrian detection plays a critical role in computer vision applications, but the performance of existing algorithms utilizing visible images is inadequate when confronted with poor lighting conditions. Conversely, infrared images deliver superior outcomes in low-light environments. Based on this issue, this study proposes the Double-EfficientDet-Improved (DEDI), a dual-stream model that integrates both visible and infrared imagery by enhancing the EfficientDet network structure. Firstly, the shuffle module is integrated into the backbone network to facilitate inter-channel information exchange within the feature layers. Secondly, by controlling the gradient path of the backbone network, the feature extraction ability is improved and the robustness is stronger. Lastly, a Multi-scale Fusion Module (MFM) is incorporated into the proposed model to harmonize information from both visible and infrared images. Experimental results demonstrate that this DEDI method achieves higher mean average precision (MAP) scores of 74.72% on the KAIST dataset and 95.13% on the LLVIP dataset, which is better than other object detection methods. DEDI visible and infrared images pedestrian detection fusion 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-3611172","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":249583341,"identity":"f6f7838b-cb6e-4423-b829-cf771baa2149","order_by":0,"name":"Chengpeng Zhang","email":"","orcid":"","institution":"Ocean University of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Chengpeng","middleName":"","lastName":"Zhang","suffix":""},{"id":249583342,"identity":"64bada2c-e394-4544-9ec9-8a0d129a6bbd","order_by":1,"name":"Miao Yu","email":"","orcid":"","institution":"Qingdao Transportation Public Service Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Miao","middleName":"","lastName":"Yu","suffix":""},{"id":249583343,"identity":"22c30c1c-e955-4c55-b027-085e049fd052","order_by":2,"name":"Jian Min","email":"","orcid":"","institution":"Ocean University of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Min","suffix":""},{"id":249583345,"identity":"6a4ac5af-e6ed-4670-80f0-2e4723b1089b","order_by":3,"name":"Min Fu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqklEQVRIiWNgGAWjYBAC9gYGhgMMFRCOBFFaeA6AtJwhVQsDYxtJWiSyEw8XzrNJ7G9gPnibh8EujwgtuRsOz9yWljjjAFuyNQ9DcjFBLfYgLbzbDiduYOAxk+ZhOJDYQJQtvHNAWvi/kaKlAWwLG5FaeN5uOMxzLM14xmE2Y8s5BslEaGHP3fyZp8ZGtr+9+eGNNxV2hLUgADOIMCBe/SgYBaNgFIwCPAAAw8M4pFABtgIAAAAASUVORK5CYII=","orcid":"","institution":"Ocean University of China","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Fu","suffix":""},{"id":249583346,"identity":"fc1d8c36-8086-464a-be6c-41c396784143","order_by":4,"name":"Bing Zheng","email":"","orcid":"","institution":"Ocean University of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Bing","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2023-11-14 15:59:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3611172/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3611172/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":75789429,"identity":"afbd982a-3c7a-449c-aa1d-0cf09df0ce4e","added_by":"auto","created_at":"2025-02-08 11:46:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3101736,"visible":true,"origin":"","legend":"","description":"","filename":"PedestriandetectionbasedonimprovedEfficientDet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3611172/v1_covered_c6df31e8-ef67-479b-ad9e-d7174f89882e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Pedestrian detection based on improved EfficientDet","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":"DEDI, visible and infrared images, pedestrian detection, fusion","lastPublishedDoi":"10.21203/rs.3.rs-3611172/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3611172/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Pedestrian detection plays a critical role in computer vision applications, but the performance of existing algorithms utilizing visible images is inadequate when confronted with poor lighting conditions. Conversely, infrared images deliver superior outcomes in low-light environments. Based on this issue, this study proposes the Double-EfficientDet-Improved (DEDI), a dual-stream model that integrates both visible and infrared imagery by enhancing the EfficientDet network structure. Firstly, the shuffle module is integrated into the backbone network to facilitate inter-channel information exchange within the feature layers. Secondly, by controlling the gradient path of the backbone network, the feature extraction ability is improved and the robustness is stronger. Lastly, a Multi-scale Fusion Module (MFM) is incorporated into the proposed model to harmonize information from both visible and infrared images. Experimental results demonstrate that this DEDI method achieves higher mean average precision (MAP) scores of 74.72\\% on the KAIST dataset and 95.13\\% on the LLVIP dataset, which is better than other object detection methods.","manuscriptTitle":"Pedestrian detection based on improved EfficientDet","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-11-17 09:30:23","doi":"10.21203/rs.3.rs-3611172/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":"a494ab32-74e3-4e32-83ad-81a0c903e3b2","owner":[],"postedDate":"November 17th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-02-08T11:38:30+00:00","versionOfRecord":[],"versionCreatedAt":"2023-11-17 09:30:23","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3611172","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3611172","identity":"rs-3611172","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}