{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-hand-articulations-tracking-using","title":"Efficient Hand Articulations Tracking using Adaptive Hand Model and Depth map","arxiv_id":"1510.00981","date":"2015-10-04","proceeding":null,"authors":["Byeongkeun Kang","Yeejin Lee","Truong Q. Nguyen"],"abstract":"Real-time hand articulations tracking is important for many applications such\nas interacting with virtual / augmented reality devices or tablets. However,\nmost of existing algorithms highly rely on expensive and high power-consuming\nGPUs to achieve real-time processing. Consequently, these systems are\ninappropriate for mobile and wearable devices. In this paper, we propose an\nefficient hand tracking system which does not require high performance GPUs. In\nour system, we track hand articulations by minimizing discrepancy between depth\nmap from sensor and computer-generated hand model. We also initialize hand pose\nat each frame using finger detection and classification. Our contributions are:\n(a) propose adaptive hand model to consider different hand shapes of users\nwithout generating personalized hand model; (b) improve the highly efficient\nframe initialization for robust tracking and automatic initialization; (c)\npropose hierarchical random sampling of pixels from each depth map to improve\ntracking accuracy while limiting required computations. To the best of our\nknowledge, it is the first system that achieves both automatic hand model\nadjustment and real-time tracking without using GPUs.","url_abs":"http://arxiv.org/abs/1510.00981v3","url_pdf":"http://arxiv.org/pdf/1510.00981v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"efficient-hand-articulations-tracking-using","repo_url":"https://github.com/byeongkeun-kang/HandTracking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}