WTGCN: Wavelet Transform Graph Convolution Network for Pedestrian Trajectory Prediction

WTGCN: Wavelet Transform Graph Convolution Network for Pedestrian Trajectory Prediction | 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 WTGCN: Wavelet Transform Graph Convolution Network for Pedestrian Trajectory Prediction Wangxing Chen, Haifeng Sang, Jinyu Wang, Zishan Zhao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3820790/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract The task of pedestrian trajectory prediction remains challenging due to variable scenarios, complex social interactions, and uncertainty in pedestrian motion. Previous trajectory prediction research only models from the time domain, which makes it difficult to accurately capture the global and detailed features of complex pedestrian social interactions and the uncertainty of pedestrian movement. These methods also ignore the relationship between scene features and the potential motion patterns of pedestrians. Therefore, we propose a wavelet transform graph convolution network to obtain accurate pedestrian potential motion patterns through time-frequency analysis. We first construct spatial and temporal graphs, then obtain the attention score matrices through the self-attention mechanism in the time domain and combine them with the scene features. Then, We utilize the two-dimensional discrete wavelet transform to generate low-frequency and high-frequency components for representing global and detailed features of spatial-temporal interactions. These components are then further processed using the asymmetric convolution, and the wavelet transform adjacency matrix is obtained through the inverse wavelet transform. We then employ graph convolution to combine the graph and the adjacency matrix to obtain spatial and temporal interaction features. Finally, we design the wavelet transform temporal convolution network to directly predict the two-dimensional Gaussian distribution parameters of the future trajectory. Extensive experiments on the ETH, UCY, and SDD datasets demonstrate that our method outperforms the state-of-the-art methods in prediction performance. pedestrian trajectory prediction wavelet transform graph convolution network scene features temporal convolution network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 28 Jan, 2024 Reviews received at journal 09 Jan, 2024 Reviewers agreed at journal 03 Jan, 2024 Reviewers invited by journal 02 Jan, 2024 Editor assigned by journal 02 Jan, 2024 Submission checks completed at journal 29 Dec, 2023 First submitted to journal 29 Dec, 2023 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-3820790","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":264339038,"identity":"ee1ada27-0124-414d-a08b-ceece6f428d6","order_by":0,"name":"Wangxing Chen","email":"","orcid":"","institution":"Shenyang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wangxing","middleName":"","lastName":"Chen","suffix":""},{"id":264339039,"identity":"471f7879-5b10-40a5-b043-27a433347d54","order_by":1,"name":"Haifeng Sang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYJACZgYGCX5+ZubDD0jSIjmznS3NgBQtDJIbzvMoSBClXL797OHXBTUWEsaHeRgMGGpsoglqMTiTl2Y945iEhNlh3gMPGI6l5TYQ1MKQY2bMwyZRZ3aYL8GAseEwYS3y/W+AWv5JSBg38xhIEKWF4UaO8WPeNgkJA2ZitRjceGPGzNsnISFxGBjICcT4Rb4/x/gzz7c6Cf7+w4cffKixIcJhDAxsiOhIIEI5CDB/IFLhKBgFo2AUjFQAAPpsODjXYMHKAAAAAElFTkSuQmCC","orcid":"","institution":"Shenyang University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Haifeng","middleName":"","lastName":"Sang","suffix":""},{"id":264339040,"identity":"098956db-6df1-4d0d-991e-7d3126766cde","order_by":2,"name":"Jinyu Wang","email":"","orcid":"","institution":"Shenyang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinyu","middleName":"","lastName":"Wang","suffix":""},{"id":264339041,"identity":"b8826c6c-eb6a-4f47-a06f-99c4a3b5273e","order_by":3,"name":"Zishan Zhao","email":"","orcid":"","institution":"Shenyang University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zishan","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2023-12-29 10:29:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3820790/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3820790/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":49042257,"identity":"4e6c9901-b8ec-4e77-9bb2-f3ee5809c9f0","added_by":"auto","created_at":"2024-01-02 05:47:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5145265,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3820790/v1_covered_e853fcee-c67d-4e6d-a0bb-ba55326eb8ff.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"WTGCN: Wavelet Transform Graph Convolution Network for Pedestrian Trajectory Prediction","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"pedestrian trajectory prediction, wavelet transform, graph convolution network, scene features, temporal convolution network","lastPublishedDoi":"10.21203/rs.3.rs-3820790/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3820790/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The task of pedestrian trajectory prediction remains challenging due to variable scenarios, complex social interactions, and uncertainty in pedestrian motion. Previous trajectory prediction research only models from the time domain, which makes it difficult to accurately capture the global and detailed features of complex pedestrian social interactions and the uncertainty of pedestrian movement. These methods also ignore the relationship between scene features and the potential motion patterns of pedestrians. Therefore, we propose a wavelet transform graph convolution network to obtain accurate pedestrian potential motion patterns through time-frequency analysis. We first construct spatial and temporal graphs, then obtain the attention score matrices through the self-attention mechanism in the time domain and combine them with the scene features. Then, We utilize the two-dimensional discrete wavelet transform to generate low-frequency and high-frequency components for representing global and detailed features of spatial-temporal interactions. These components are then further processed using the asymmetric convolution, and the wavelet transform adjacency matrix is obtained through the inverse wavelet transform. We then employ graph convolution to combine the graph and the adjacency matrix to obtain spatial and temporal interaction features. Finally, we design the wavelet transform temporal convolution network to directly predict the two-dimensional Gaussian distribution parameters of the future trajectory. Extensive experiments on the ETH, UCY, and SDD datasets demonstrate that our method outperforms the state-of-the-art methods in prediction performance.","manuscriptTitle":"WTGCN: Wavelet Transform Graph Convolution Network for Pedestrian Trajectory Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-02 05:39:49","doi":"10.21203/rs.3.rs-3820790/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-01-29T02:55:53+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-09T10:34:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"2603e6e8-d881-4b13-8dff-efc2ed9c8332","date":"2024-01-03T13:58:50+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-03T03:47:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-02T16:16:26+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-12-29T13:00:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2023-12-29T10:17:52+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1123f998-d9e4-4ae9-b8d7-c22531c7b80c","owner":[],"postedDate":"January 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-06-11T01:40:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-02 05:39:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3820790","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3820790","identity":"rs-3820790","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}