Spatiotemporal GAN with Multi-Head Attention for Vehicle Trajectory Denoising

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract High-precision and high-quality vehicle trajectory data form the foundation for core applications in Intelligent Transportation Systems (ITS), such as traffic flow analysis, path planning, and autonomous driving. However, the trajectory data collected in practice often suffer from quality issues due to factors such as sensor noise, data transmission loss, and environmental interference, which seriously affect the performance of subsequent applications. To address this challenge, this paper proposes an innovative framework based on Generative Adversarial Networks (GANs), aimed at efficiently denoising and completing trajectory data. The framework deeply integrates a multi-head attention mechanism, a spatiotemporal convolutional network, and residual connections, and is optimized using a dual loss function. Specifically, the multi-head attention mechanism effectively captures long-range temporal dependencies within the trajectory data, significantly enhancing the model’s ability to understand complex motion patterns. The spatiotemporal convolutional network, through multi-scale feature extraction and residual connections, strengthens the model's perception and representation of local spatiotemporal features, and effectively mitigates gradient issues during deep network training. The combination of the dual loss function (reconstruction loss and adversarial loss) ensures that the generated data closely approximates the real data distribution while maintaining high-precision reconstruction. This study validates the proposed model using real UAV-collected vehicle trajectory data from the open traffic data platform of the Swiss Federal Institute of Technology Lausanne (EPFL). The dataset includes trajectory data from five continuous 30-minute time windows during the morning peak period on October 24, 2018 (08:30 − 11:00). Experimental results show that the proposed model demonstrates exceptional performance on the UAV trajectory dataset. Compared to traditional methods, trajectory reconstruction accuracy is significantly improved, with an average improvement rate of 85.6%, and the correlation coefficients of key features (such as latitude, longitude, and speed) exceed 0.92. This research provides an effective solution to improve the quality of trajectory data in intelligent transportation systems and holds significant theoretical and practical value for applications in autonomous driving, urban planning, and traffic management.
Full text 38,876 characters · extracted from preprint-html · click to expand
Spatiotemporal GAN with Multi-Head Attention for Vehicle Trajectory Denoising | 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 Spatiotemporal GAN with Multi-Head Attention for Vehicle Trajectory Denoising Kefeng Wang, Jilin Jiang, Hui He, Xinyu He This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8017943/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 12 You are reading this latest preprint version Abstract High-precision and high-quality vehicle trajectory data form the foundation for core applications in Intelligent Transportation Systems (ITS), such as traffic flow analysis, path planning, and autonomous driving. However, the trajectory data collected in practice often suffer from quality issues due to factors such as sensor noise, data transmission loss, and environmental interference, which seriously affect the performance of subsequent applications. To address this challenge, this paper proposes an innovative framework based on Generative Adversarial Networks (GANs), aimed at efficiently denoising and completing trajectory data. The framework deeply integrates a multi-head attention mechanism, a spatiotemporal convolutional network, and residual connections, and is optimized using a dual loss function. Specifically, the multi-head attention mechanism effectively captures long-range temporal dependencies within the trajectory data, significantly enhancing the model’s ability to understand complex motion patterns. The spatiotemporal convolutional network, through multi-scale feature extraction and residual connections, strengthens the model's perception and representation of local spatiotemporal features, and effectively mitigates gradient issues during deep network training. The combination of the dual loss function (reconstruction loss and adversarial loss) ensures that the generated data closely approximates the real data distribution while maintaining high-precision reconstruction. This study validates the proposed model using real UAV-collected vehicle trajectory data from the open traffic data platform of the Swiss Federal Institute of Technology Lausanne (EPFL). The dataset includes trajectory data from five continuous 30-minute time windows during the morning peak period on October 24, 2018 (08:30 − 11:00). Experimental results show that the proposed model demonstrates exceptional performance on the UAV trajectory dataset. Compared to traditional methods, trajectory reconstruction accuracy is significantly improved, with an average improvement rate of 85.6%, and the correlation coefficients of key features (such as latitude, longitude, and speed) exceed 0.92. This research provides an effective solution to improve the quality of trajectory data in intelligent transportation systems and holds significant theoretical and practical value for applications in autonomous driving, urban planning, and traffic management. Physical sciences/Engineering Physical sciences/Mathematics and computing Generative adversarial network trajectory data denoising completion unmanned aerial vehicle multi-head attention spatiotemporal convolution intelligent transportation system Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 31 Jan, 2026 Reviews received at journal 30 Jan, 2026 Reviews received at journal 29 Jan, 2026 Reviewers agreed at journal 29 Jan, 2026 Reviewers agreed at journal 27 Jan, 2026 Reviewers agreed at journal 15 Dec, 2025 Reviews received at journal 30 Nov, 2025 Reviewers agreed at journal 22 Nov, 2025 Reviewers invited by journal 12 Nov, 2025 Editor assigned by journal 04 Nov, 2025 Submission checks completed at journal 04 Nov, 2025 First submitted to journal 03 Nov, 2025 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-8017943","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":549198663,"identity":"f38b346f-5b65-4900-b0fa-f066149a1f76","order_by":0,"name":"Kefeng Wang","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Kefeng","middleName":"","lastName":"Wang","suffix":""},{"id":549198664,"identity":"23ceac67-ccf1-4889-a290-259657a13ab5","order_by":1,"name":"Jilin Jiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYBACxmbmhgMMBv94+CXA/ANgUgK/FkagloIDMpIziNUC1NTAwPDhgI3BDWK1MLczNh4uMLjDY3y7+eiGDwx38gwOMB+8zcNgl4fPYYdnGDzjMbtzLO3mDIZnxQYH2JKteRiSi/Fq4TFg5jG7kWMGNPxw4oYDPGbSPAwHEhsIaTGeAdTyB6yF/xsxWoBIAqiFAWILGzFa0ngkbqSl3ewxOFwseZjN2HKOQTJOLYb9hw9/5vljY88/I/nYjR8Vh/P4jjc/vPGmwg63FlQJA4YEBmYIAyeQRxdIwK12FIyCUTAKRioAAH1AXLPfb09UAAAAAElFTkSuQmCC","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Jilin","middleName":"","lastName":"Jiang","suffix":""},{"id":549198665,"identity":"f020830b-abe9-4e52-92fd-c3b3fa8ea88d","order_by":2,"name":"Hui He","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"He","suffix":""},{"id":549198666,"identity":"531bb3be-37f8-43c0-94d1-dd876bbde94f","order_by":3,"name":"Xinyu He","email":"","orcid":"","institution":"Henan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"He","suffix":""}],"badges":[],"createdAt":"2025-11-03 10:23:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8017943/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8017943/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96605832,"identity":"3144699f-d990-4198-8399-a20b230caf42","added_by":"auto","created_at":"2025-11-24 09:24:10","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4586790,"visible":true,"origin":"","legend":"","description":"","filename":"Article.docx","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/692fb81dd26d84cc05a2948e.docx"},{"id":96583371,"identity":"d4a6260d-81ee-4652-9aef-e1453cc37e52","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6550,"visible":true,"origin":"","legend":"","description":"","filename":"1d23b56ec5a842b3b522ca7db93246dc.json","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/7fee6b133ec71cae03943a5e.json"},{"id":96605074,"identity":"e8f3afde-0be5-4bd9-91ff-11485720781e","added_by":"auto","created_at":"2025-11-24 09:17:58","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":208579,"visible":true,"origin":"","legend":"","description":"","filename":"1d23b56ec5a842b3b522ca7db93246dc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/4d8832082ba583805838cb11.xml"},{"id":96605829,"identity":"65121d05-b8fc-45c1-9ffd-718dc2881ee9","added_by":"auto","created_at":"2025-11-24 09:24:09","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70960,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/36ef29063ceb21e293d09916.png"},{"id":96583393,"identity":"10178e76-c3aa-4f67-9d4d-31d8649a6b68","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":172806,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/def91df98e01b7e6b330ebe4.png"},{"id":96583373,"identity":"fc9425cd-bb8e-4a59-a77b-19d20d4f6708","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":287132,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/f662fe191d150f47ce60f399.png"},{"id":96605480,"identity":"e74f9d36-2515-4727-bc02-a233bc2fbd34","added_by":"auto","created_at":"2025-11-24 09:23:12","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":331956,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/5a5421723f8df60c2342a7bd.png"},{"id":96583367,"identity":"40cb3c59-0cb5-4d49-8e7f-a859b79d395e","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":325026,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/5e982d6cbe19318d5691673a.png"},{"id":96583380,"identity":"8c98fcf5-7171-489c-a739-85bfd1eac525","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":287203,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/410b200e923ec1b18f11455f.png"},{"id":96583370,"identity":"89f156e3-c988-4491-8537-4661dda40e8c","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":326499,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/50d67f4400e616f9c33a5478.png"},{"id":96583372,"identity":"0975ef3a-1b57-46c2-8a16-8484701e5558","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":82157,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/9bcace7218fe471a7c0dfcce.png"},{"id":96583394,"identity":"ea4a512f-4b9a-4053-b521-c4a71a21f894","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":336268,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/bb6f46833ea52520ee99ab36.png"},{"id":96605904,"identity":"c7036084-95f1-4a86-8d3f-fbb469c9f6b5","added_by":"auto","created_at":"2025-11-24 09:24:20","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56164,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/ac8aa86134ad1c6b55e6fc5c.png"},{"id":96583374,"identity":"8114f8d1-9e59-4834-9718-068cf9c32669","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85570,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/0e0ea03425320d8c21d57a1d.png"},{"id":96583396,"identity":"bebcce22-035e-4eb7-b355-ab62518eb2ad","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":62477,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/e5ae72edd720926e24df211b.png"},{"id":96605510,"identity":"372b4e82-e7cd-42c2-88fe-31dcb0e0631c","added_by":"auto","created_at":"2025-11-24 09:23:19","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108026,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage20.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/4abaed6e2d1bc3c1bda8887b.png"},{"id":96583408,"identity":"cf46f81f-cdc2-4044-8112-29ce354210d5","added_by":"auto","created_at":"2025-11-24 03:34:47","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":138475,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/c4eb255990b541849fcf12fa.png"},{"id":96583401,"identity":"6a3554eb-0e19-4fd3-8c0d-490c373183a8","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":297152,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage22.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/439529d2050dbf346d3d8122.png"},{"id":96583418,"identity":"69ae4d88-c69e-470a-9ddc-2f2a625d1e30","added_by":"auto","created_at":"2025-11-24 03:34:48","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":148599,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage23.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/2cb42935532440f443f4ec24.png"},{"id":96583415,"identity":"1ee29bf4-eb4c-4e7a-9d08-5b294e49dbb4","added_by":"auto","created_at":"2025-11-24 03:34:47","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":145384,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage24.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/0265293047156484f7ae5e7e.png"},{"id":96583382,"identity":"0d976b1d-ffc3-45d4-bc9f-835a3eda5303","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":206879,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage25.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/811d4c1e90dfe495baeb8750.png"},{"id":96583406,"identity":"0ff0ed39-084c-4ea2-a114-074bc25e4da3","added_by":"auto","created_at":"2025-11-24 03:34:47","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79913,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage26.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/effef69c5d6c8e023f721e04.png"},{"id":96583376,"identity":"71e7abe8-a148-4662-a559-15c10fe8109f","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70046,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/b3ac78da725ae9010b6bc961.png"},{"id":96583403,"identity":"adb07593-964c-40e5-a2fc-62b8c9339dfc","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123669,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/819bcbd901ea7f8a4eb04d02.png"},{"id":96583390,"identity":"c1f82907-dacf-4ece-8bab-fe7f864e30bc","added_by":"auto","created_at":"2025-11-24 03:34:45","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":231379,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/3cbc229f1c821fc926487b00.png"},{"id":96583386,"identity":"ff67dcfb-6f9b-4d0a-872f-d73923efa407","added_by":"auto","created_at":"2025-11-24 03:34:45","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168658,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/cd01501c29bb9b6ca2c324f7.png"},{"id":96583364,"identity":"aec09531-3804-42eb-ad22-8bf300d919de","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99397,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/4d0e11b984691d582676db2e.png"},{"id":96583381,"identity":"03b70b2f-b7c4-4b25-90b8-da7059e43527","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":123282,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/a9bcba7c72576a4cdbbb1d54.png"},{"id":96583368,"identity":"bf27c873-103d-4be1-b985-3d43591f478d","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":133696,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/e88ef962a154c21773100b01.png"},{"id":96605466,"identity":"879c8f51-20cc-4d30-8189-59e27548750c","added_by":"auto","created_at":"2025-11-24 09:23:07","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26586,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/3abc33f9041114c3652bb55e.png"},{"id":96583369,"identity":"a4d5289c-cd07-4f31-ac24-497e44aa43e0","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58793,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/5d50cfd9d15c8fe3bd8453dd.png"},{"id":96583413,"identity":"5b92142d-3bbc-497a-98c9-d41ce40cdba0","added_by":"auto","created_at":"2025-11-24 03:34:47","extension":"png","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86150,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/3c656f2a1e42fbf7a633bd56.png"},{"id":96583379,"identity":"5af17711-0584-407f-b991-66a3002686e5","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":97218,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/264a896deabb91d7d59b89f2.png"},{"id":96583421,"identity":"1ff380c8-ef86-4b89-a4a1-c7b076530a2a","added_by":"auto","created_at":"2025-11-24 03:34:48","extension":"png","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95438,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/c975f6c7b9704c99b9197f6c.png"},{"id":96583397,"identity":"fd7137a4-c373-49f0-8f2d-9501247064e6","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86724,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/6f0917ca1b4ce90433f211f6.png"},{"id":96583400,"identity":"c3847ed4-1ecf-44b1-8cc4-22a226e4c8c2","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94248,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/ff8569592ce1b70673b5b374.png"},{"id":96583417,"identity":"75a94a6d-d99e-4b88-ac48-3cbfcfc49457","added_by":"auto","created_at":"2025-11-24 03:34:48","extension":"png","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29953,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/7fd91df063aeba9ebfd7b5fb.png"},{"id":96583392,"identity":"77aef77a-c290-4245-a358-6587374caaf6","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78704,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/8164825a416a759c1ae7f1c0.png"},{"id":96604949,"identity":"1ffbc5df-b410-4fcb-8f0c-6a9144de82b0","added_by":"auto","created_at":"2025-11-24 09:16:41","extension":"png","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16205,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/baa72712e2b2d8acc8b0a2e7.png"},{"id":96605168,"identity":"2357ffdb-43f6-4714-90d6-fdd63ac032eb","added_by":"auto","created_at":"2025-11-24 09:20:31","extension":"png","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21471,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/4e999a76a6b2260d371dd197.png"},{"id":96583366,"identity":"30f3939d-db54-4886-9748-c5414a7e1661","added_by":"auto","created_at":"2025-11-24 03:34:43","extension":"png","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25818,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/27f9296cfbab9f896666b24b.png"},{"id":96583405,"identity":"0e99f731-77fd-4592-b1f5-e40f7ad95e3e","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":34959,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage20.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/aa6edd634c82612a8a0bae53.png"},{"id":96583416,"identity":"3a45f564-c4cf-4808-9c65-520c7cc08d75","added_by":"auto","created_at":"2025-11-24 03:34:48","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24321,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage21.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/49e130d4c0164b16258234ba.png"},{"id":96604675,"identity":"77d5943a-c112-4d0d-939b-cdac279d1b1e","added_by":"auto","created_at":"2025-11-24 09:14:33","extension":"png","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80851,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage22.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/c3109e4ac4afa44c5fd442cd.png"},{"id":96605237,"identity":"e49323eb-13a5-4b5e-ae60-f577a7e19e28","added_by":"auto","created_at":"2025-11-24 09:21:44","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28669,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage23.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/ce5081c1741ecc7ea23010c5.png"},{"id":96605445,"identity":"6a535cfd-06f4-45f3-972f-a8ad03bc93ab","added_by":"auto","created_at":"2025-11-24 09:23:04","extension":"png","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38809,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage24.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/b855a09aef2327cb4ad55956.png"},{"id":96583398,"identity":"1e6dcf58-469a-485c-8e8d-3a13c9eb9d6f","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49800,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage25.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/d6092310ea76e53f64539e53.png"},{"id":96605413,"identity":"3a01894e-4ec4-4d46-8f53-554c934b438a","added_by":"auto","created_at":"2025-11-24 09:22:50","extension":"png","order_by":47,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20219,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage26.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/a7ed3aa70fbf250809c35042.png"},{"id":96583404,"identity":"9130fdb8-a2a4-4973-acac-98054cff4ddc","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":48,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24146,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/dc1f13a6cd64ae4e72d68fc4.png"},{"id":96583399,"identity":"b17e04d7-4cc4-4b2b-b8d2-24639a9478d9","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"png","order_by":49,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36557,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/19aec90a56bf79fc3b6c9d36.png"},{"id":96583414,"identity":"97bb7a2c-38c8-411a-98c3-fc24df25a15c","added_by":"auto","created_at":"2025-11-24 03:34:47","extension":"png","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54568,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/2a03bb41178a19967a0bcbcc.png"},{"id":96583419,"identity":"49cb98f3-5930-4a62-816c-b860e2b66c36","added_by":"auto","created_at":"2025-11-24 03:34:48","extension":"png","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51168,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/aa6699b32ff8469dd0cad200.png"},{"id":96583384,"identity":"9d1a8452-a0fa-49bb-bb54-2f7c53c93f38","added_by":"auto","created_at":"2025-11-24 03:34:44","extension":"png","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36355,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/32ef383c2f1a1708d991e714.png"},{"id":96583420,"identity":"32c5c306-851a-4b48-86a0-038cf13aae70","added_by":"auto","created_at":"2025-11-24 03:34:48","extension":"png","order_by":53,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43740,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/1320cb55e04fda3fda510075.png"},{"id":96583389,"identity":"1c84fc51-37f2-4dc1-8c8d-9a404867478a","added_by":"auto","created_at":"2025-11-24 03:34:45","extension":"png","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48644,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/c953bc4d9c2a354141fa0e94.png"},{"id":96583402,"identity":"698b6141-44d7-4ea9-84b6-1f41f14b3d30","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"xml","order_by":55,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":209292,"visible":true,"origin":"","legend":"","description":"","filename":"1d23b56ec5a842b3b522ca7db93246dc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/f83805497b342fd9d8fba17e.xml"},{"id":96583395,"identity":"3692fbb6-4539-4c8c-97a8-9b99c2c48b66","added_by":"auto","created_at":"2025-11-24 03:34:46","extension":"html","order_by":56,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":224828,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1/958af933c2c345d78db5e941.html"},{"id":96608472,"identity":"0ef064d7-7ee4-4286-84ad-c8e1a376521a","added_by":"auto","created_at":"2025-11-24 09:28:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3266243,"visible":true,"origin":"","legend":"","description":"","filename":"Article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8017943/v1_covered_04a6dc47-ff3f-4c7c-89e8-fa1a06d71149.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Spatiotemporal GAN with Multi-Head Attention for Vehicle Trajectory Denoising","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Generative adversarial network, trajectory data, denoising, completion, unmanned aerial vehicle, multi-head attention, spatiotemporal convolution, intelligent transportation system","lastPublishedDoi":"10.21203/rs.3.rs-8017943/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8017943/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHigh-precision and high-quality vehicle trajectory data form the foundation for core applications in Intelligent Transportation Systems (ITS), such as traffic flow analysis, path planning, and autonomous driving. However, the trajectory data collected in practice often suffer from quality issues due to factors such as sensor noise, data transmission loss, and environmental interference, which seriously affect the performance of subsequent applications. To address this challenge, this paper proposes an innovative framework based on Generative Adversarial Networks (GANs), aimed at efficiently denoising and completing trajectory data. The framework deeply integrates a multi-head attention mechanism, a spatiotemporal convolutional network, and residual connections, and is optimized using a dual loss function. Specifically, the multi-head attention mechanism effectively captures long-range temporal dependencies within the trajectory data, significantly enhancing the model\u0026rsquo;s ability to understand complex motion patterns. The spatiotemporal convolutional network, through multi-scale feature extraction and residual connections, strengthens the model's perception and representation of local spatiotemporal features, and effectively mitigates gradient issues during deep network training. The combination of the dual loss function (reconstruction loss and adversarial loss) ensures that the generated data closely approximates the real data distribution while maintaining high-precision reconstruction. This study validates the proposed model using real UAV-collected vehicle trajectory data from the open traffic data platform of the Swiss Federal Institute of Technology Lausanne (EPFL). The dataset includes trajectory data from five continuous 30-minute time windows during the morning peak period on October 24, 2018 (08:30\u0026thinsp;\u0026minus;\u0026thinsp;11:00). Experimental results show that the proposed model demonstrates exceptional performance on the UAV trajectory dataset. Compared to traditional methods, trajectory reconstruction accuracy is significantly improved, with an average improvement rate of 85.6%, and the correlation coefficients of key features (such as latitude, longitude, and speed) exceed 0.92. This research provides an effective solution to improve the quality of trajectory data in intelligent transportation systems and holds significant theoretical and practical value for applications in autonomous driving, urban planning, and traffic management.\u003c/p\u003e","manuscriptTitle":"Spatiotemporal GAN with Multi-Head Attention for Vehicle Trajectory Denoising","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-24 03:34:36","doi":"10.21203/rs.3.rs-8017943/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-31T06:29:38+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-31T04:51:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-29T06:08:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"3883528230913651183160243669431387565","date":"2026-01-29T05:44:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"336210893446543115380904133656986745998","date":"2026-01-28T02:43:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"12165071303014324026933963788697864384","date":"2025-12-16T02:17:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-30T05:22:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161970002598464345306717693882586561057","date":"2025-11-22T16:23:49+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-12T10:25:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-04T14:58:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-04T14:58:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-11-03T10:14:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2b44659b-5b42-4849-827c-2692f311c220","owner":[],"postedDate":"November 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":58440169,"name":"Physical sciences/Engineering"},{"id":58440170,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-15T06:55:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-24 03:34:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8017943","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8017943","identity":"rs-8017943","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-24T02:00:01.246996+00:00
License: CC-BY-4.0