Research on lightweight terminal mark detection method based on improved DBNet network

Research on lightweight terminal mark detection method based on improved DBNet network | 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 Research on lightweight terminal mark detection method based on improved DBNet network Jingqi Wang, Peng Chen, Qiang Xue, Shuohe Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6601425/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 To address the intricate backdrop and distorted deformation issues in substation terminal marking identification, a lightweight detection method utilizing an enhanced DBNet network is proposed. To address the intricate background factors in the terminal marking image, the backbone network is substituted with the lightweight MobileViTv3, and the DCA module of the dual cross-attention mechanism is incorporated to capture both local details and global contextual information. The Dynamic Snake Convolution (DSConv) is implemented within the feature pyramid to dynamically modify the sampling paths of the convolution kernel, while the offset generation network is revised to an MLP for enhanced accuracy in offset generation. Additionally, the upsampling operation of the FPN layer is replaced with the lightweight upsampling operator CARAFE, which adjusts the upsampling kernel based on the input feature map content. Furthermore, the Dice loss function is integrated into the DBNet architecture to enhance network performance. The experimental findings indicate that the detection accuracy F1 of the enhanced lightweight DBNet network attains 93.4%, surpassing the original network by 4.9 percentage points, while the number of parameters is merely 23.6% of that in the original model, thereby adequately fulfilling the practical requirements for detecting twisted and deformed terminal markings in a complex background. Text detection DBNet༛MobileViTv3༛DSConv༛CARAFE 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-6601425","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":455267334,"identity":"540afc84-2533-4ffe-8e16-5489ea70bda6","order_by":0,"name":"Jingqi Wang","email":"","orcid":"","institution":"Shijiazhuang Tiedao University","correspondingAuthor":false,"prefix":"","firstName":"Jingqi","middleName":"","lastName":"Wang","suffix":""},{"id":455267335,"identity":"29cfcedc-2281-45a0-9a0f-acb6017ef8a0","order_by":1,"name":"Peng Chen","email":"","orcid":"","institution":"Hebei KunNeng Electric Power Engineering Consulting Co., Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"Chen","suffix":""},{"id":455267336,"identity":"e3bc53bb-21dc-457d-9377-aa31b3b0e46d","order_by":2,"name":"Qiang Xue","email":"","orcid":"","institution":"Shijiazhuang Tiedao University","correspondingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Xue","suffix":""},{"id":455267340,"identity":"014fd4cb-d940-4a9e-97aa-80ad987bc3de","order_by":3,"name":"Shuohe Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYLACxgYGBgMG5gMMCSRqYUsgWQuPAXGqDY6fPfzy547DcubsPZ8/PNxhx8Df3o3fMoMzeWnWvGcOG1v2nN0mkXgmmUHizNkNeLWYHcgxM2ZsO5y44UbuNobENmYGA4lcAlrOvzEz/AnScv/N4w+JbfVEaLmRY/yAF2wLD4NEYtthwlrsb7wxY+ZtSzc2OJNmBtRynIegXyT7c4w//myzljM4fvgxkFEtx9/ei18LELBJIPN4CCkHAeYPxKgaBaNgFIyCEQwArOFNyEbrHzcAAAAASUVORK5CYII=","orcid":"","institution":"Shijiazhuang Tiedao University","correspondingAuthor":true,"prefix":"","firstName":"Shuohe","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-05-06 09:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6601425/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6601425/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88058254,"identity":"3fc881d5-3f74-48be-8447-d2768c8a62a6","added_by":"auto","created_at":"2025-08-01 00:31:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":753734,"visible":true,"origin":"","legend":"","description":"","filename":"ResearchonlightweightterminalmarkdetectionmethodbasedonimprovedDBNetnetwork.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6601425/v1_covered_822b73cb-0da1-4640-9496-fab6028ce27b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on lightweight terminal mark detection method based on improved DBNet network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Text detection, DBNet༛MobileViTv3༛DSConv༛CARAFE","lastPublishedDoi":"10.21203/rs.3.rs-6601425/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6601425/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTo address the intricate backdrop and distorted deformation issues in substation terminal marking identification, a lightweight detection method utilizing an enhanced DBNet network is proposed. To address the intricate background factors in the terminal marking image, the backbone network is substituted with the lightweight MobileViTv3, and the DCA module of the dual cross-attention mechanism is incorporated to capture both local details and global contextual information. The Dynamic Snake Convolution (DSConv) is implemented within the feature pyramid to dynamically modify the sampling paths of the convolution kernel, while the offset generation network is revised to an MLP for enhanced accuracy in offset generation. Additionally, the upsampling operation of the FPN layer is replaced with the lightweight upsampling operator CARAFE, which adjusts the upsampling kernel based on the input feature map content. Furthermore, the Dice loss function is integrated into the DBNet architecture to enhance network performance. The experimental findings indicate that the detection accuracy F1 of the enhanced lightweight DBNet network attains 93.4%, surpassing the original network by 4.9 percentage points, while the number of parameters is merely 23.6% of that in the original model, thereby adequately fulfilling the practical requirements for detecting twisted and deformed terminal markings in a complex background.\u003c/p\u003e","manuscriptTitle":"Research on lightweight terminal mark detection method based on improved DBNet network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-14 03:27:05","doi":"10.21203/rs.3.rs-6601425/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":"60290fbe-824f-4200-a5a9-64f3739467d4","owner":[],"postedDate":"May 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-01T00:23:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-14 03:27:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6601425","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6601425","identity":"rs-6601425","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}