{"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/a-region-based-gauss-newton-approach-to-real","title":"A Region-based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking","arxiv_id":"1807.02087","date":"2018-07-05","proceeding":null,"authors":["Henning Tjaden","Ulrich Schwanecke","Elmar Schömer","Daniel Cremers"],"abstract":"We propose an algorithm for real-time 6DOF pose tracking of rigid 3D objects\nusing a monocular RGB camera. The key idea is to derive a region-based cost\nfunction using temporally consistent local color histograms. While such\nregion-based cost functions are commonly optimized using first-order gradient\ndescent techniques, we systematically derive a Gauss-Newton optimization scheme\nwhich gives rise to drastically faster convergence and highly accurate and\nrobust tracking performance. We furthermore propose a novel complex dataset\ndedicated for the task of monocular object pose tracking and make it publicly\navailable to the community. To our knowledge, it is the first to address the\ncommon and important scenario in which both the camera as well as the objects\nare moving simultaneously in cluttered scenes. In numerous experiments -\nincluding our own proposed dataset - we demonstrate that the proposed\nGauss-Newton approach outperforms existing approaches, in particular in the\npresence of cluttered backgrounds, heterogeneous objects and partial\nocclusions.","url_abs":"http://arxiv.org/abs/1807.02087v2","url_pdf":"http://arxiv.org/pdf/1807.02087v2.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":"a-region-based-gauss-newton-approach-to-real","repo_url":"https://github.com/henningtjaden/RBOT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"pose-tracking","task_name":"Pose Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.02087","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}