{"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/dynamics-based-3d-skeletal-hand-tracking","title":"Dynamics Based 3D Skeletal Hand Tracking","arxiv_id":"1705.07640","date":"2017-05-22","proceeding":null,"authors":["Stan Melax","Leonid Keselman","Sterling Orsten"],"abstract":"Tracking the full skeletal pose of the hands and fingers is a challenging\nproblem that has a plethora of applications for user interaction. Existing\ntechniques either require wearable hardware, add restrictions to user pose, or\nrequire significant computation resources. This research explores a new\napproach to tracking hands, or any articulated model, by using an augmented\nrigid body simulation. This allows us to phrase 3D object tracking as a linear\ncomplementarity problem with a well-defined solution. Based on a depth sensor's\nsamples, the system generates constraints that limit motion orthogonal to the\nrigid body model's surface. These constraints, along with prior motion,\ncollision/contact constraints, and joint mechanics, are resolved with a\nprojected Gauss-Seidel solver. Due to camera noise properties and attachment\nerrors, the numerous surface constraints are impulse capped to avoid\noverpowering mechanical constraints. To improve tracking accuracy, multiple\nsimulations are spawned at each frame and fed a variety of heuristics,\nconstraints and poses. A 3D error metric selects the best-fit simulation,\nhelping the system handle challenging hand motions. Such an approach enables\nreal-time, robust, and accurate 3D skeletal tracking of a user's hand on a\nvariety of depth cameras, while only utilizing a single x86 CPU core for\nprocessing.","url_abs":"http://arxiv.org/abs/1705.07640v1","url_pdf":"http://arxiv.org/pdf/1705.07640v1.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":"dynamics-based-3d-skeletal-hand-tracking","repo_url":"https://github.com/melax/hand_tracking_samples","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-object-tracking","task_name":"3D Object Tracking"},{"task_slug":null,"task_name":"CPU"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.07640","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}