Taekwondo training motion capture technology based on improved Transformer-GCN

Taekwondo training motion capture technology based on improved Transformer-GCN | 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 Taekwondo training motion capture technology based on improved Transformer-GCN zhiyong li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8572834/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 issues of insufficient motion capture accuracy, poor scoring consistency, and delayed feedback in Taekwondo training, a Taekwondo motion capture model combining an improved Transform and graph convolutional network is developed. The model introduces a multi-modal skeleton feature fusion mechanism, and combines a sliding window scoring structure with a temporal modeling module to achieve precise capture and rapid scoring feedback for continuous Taekwondo movements. Validated on two standard open datasets in the field, the results show that with a residual link weight coefficient set to 0.5 and a multi-scale attention fusion coefficient set to 0.6, the model achieves a scoring consistency of up to 91.9%, an F1 score improved to 0.94, and a feedback delay minimized to 38.6ms. Further simulation experiments demonstrate that the model maintains an average pose reconstruction error as low as 2.91 in four typical training environments. In the recognition and scoring of four classic Taekwondo movements, the median of the inter-score variance is as low as 0.042, outperforming the three existing mainstream models. The study also verifies the model's superior key joint recognition capabilities under conditions of multiple person interference, occlusion, and complex movements through real teaching video testing. In summary, the proposed Taekwondo motion capture model combining an improved Transform and graph convolutional network demonstrates superior scoring accuracy and structural recognition capabilities in complex training environments, providing a feasible path and technical support for the construction of intelligent Taekwondo teaching and motion evaluation systems. Physical sciences/Engineering Physical sciences/Mathematics and computing Motion capture Taekwondo Action recognition Transformer GCN 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-8572834","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":578529725,"identity":"713ec526-1372-455a-ac7a-90a4a4dbbaee","order_by":0,"name":"zhiyong li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIie2QMWrDQBBFRyzIzYJcjjDYV5ggcBLQYXYxKI0JgRwgKxasxpB2j6EbRGKIz+AyaVKrFMQkkbtUuy4D2VdM9R+fPwCRyJ9EmOng08tz3YwDlcsLlOSslEmLbHL3UBWXKlXSwp1ZyIF1UFg5Xb8NwOIaelOUJBTM+LX1djhtrxxwemtrs9lSeg+yqo4+RaDeLSSwhK43vCX5CCjXXiVF3XyegBE6XdsbQm1CipxaxDSfqNNWAFFYQflu8z2UKnf9LtmTKtLQllWz6YcRUGVZ8wHj6XuZzfjgVWCuprd9/V7njZ/JumAkEolE/js/S/9KxhYaNhQAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"zhiyong","middleName":"","lastName":"li","suffix":""}],"badges":[],"createdAt":"2026-01-11 10:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8572834/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8572834/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100967370,"identity":"4a33eb9f-9645-4684-8e60-d63030191a9f","added_by":"auto","created_at":"2026-01-23 09:35:25","extension":"doc","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3611648,"visible":true,"origin":"","legend":"","description":"","filename":"11TransformerGCN.doc","url":"https://assets-eu.researchsquare.com/files/rs-8572834/v1/dd562ddcc1ff2e4e02245763.doc"},{"id":100967372,"identity":"4ccabe6f-ce2f-40da-8d50-1cfa0bece7f9","added_by":"auto","created_at":"2026-01-23 09:35:25","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3836,"visible":true,"origin":"","legend":"","description":"","filename":"49ee2abc74764220ba47ed957764965e.json","url":"https://assets-eu.researchsquare.com/files/rs-8572834/v1/b0f5c105d91f406bfd9ca04c.json"},{"id":100967368,"identity":"eca2fd67-26c7-4c4e-b985-829f3aa546e8","added_by":"auto","created_at":"2026-01-23 09:35:24","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32641,"visible":true,"origin":"","legend":"","description":"","filename":"Statement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8572834/v1/7bc4d791b44aa0101688fc56.pdf"},{"id":100967371,"identity":"64cec1ff-a208-4fe6-9f94-0c2639eb3229","added_by":"auto","created_at":"2026-01-23 09:35:25","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":982423,"visible":true,"origin":"","legend":"","description":"","filename":"1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8572834/v1/b047cf7f0514f8137f2b1510.pdf"},{"id":106851383,"identity":"5c9a9109-3d97-4f3c-99cf-f3d52906988c","added_by":"auto","created_at":"2026-04-14 06:27:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":537223,"visible":true,"origin":"","legend":"","description":"","filename":"11TransformerGCN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8572834/v1_covered_e440b6a1-3d6e-4766-895f-3f9cef8c8e8c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Taekwondo training motion capture technology based on improved Transformer-GCN","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":"Motion capture, Taekwondo, Action recognition, Transformer, GCN","lastPublishedDoi":"10.21203/rs.3.rs-8572834/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8572834/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"To address the issues of insufficient motion capture accuracy, poor scoring consistency, and delayed feedback in Taekwondo training, a Taekwondo motion capture model combining an improved Transform and graph convolutional network is developed. The model introduces a multi-modal skeleton feature fusion mechanism, and combines a sliding window scoring structure with a temporal modeling module to achieve precise capture and rapid scoring feedback for continuous Taekwondo movements. Validated on two standard open datasets in the field, the results show that with a residual link weight coefficient set to 0.5 and a multi-scale attention fusion coefficient set to 0.6, the model achieves a scoring consistency of up to 91.9%, an F1 score improved to 0.94, and a feedback delay minimized to 38.6ms. Further simulation experiments demonstrate that the model maintains an average pose reconstruction error as low as 2.91 in four typical training environments. In the recognition and scoring of four classic Taekwondo movements, the median of the inter-score variance is as low as 0.042, outperforming the three existing mainstream models. The study also verifies the model's superior key joint recognition capabilities under conditions of multiple person interference, occlusion, and complex movements through real teaching video testing. In summary, the proposed Taekwondo motion capture model combining an improved Transform and graph convolutional network demonstrates superior scoring accuracy and structural recognition capabilities in complex training environments, providing a feasible path and technical support for the construction of intelligent Taekwondo teaching and motion evaluation systems.","manuscriptTitle":"Taekwondo training motion capture technology based on improved Transformer-GCN","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-23 09:35:20","doi":"10.21203/rs.3.rs-8572834/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":"e046c571-5421-44fc-b424-cb2ca264f612","owner":[],"postedDate":"January 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61555349,"name":"Physical sciences/Engineering"},{"id":61555350,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-14T06:25:00+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-23 09:35:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8572834","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8572834","identity":"rs-8572834","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}