{"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/combined-image-and-world-space-tracking-in","title":"Combined Image- and World-Space Tracking in Traffic Scenes","arxiv_id":"1809.07357","date":"2018-09-19","proceeding":null,"authors":["Aljosa Osep","Wolfgang Mehner","Markus Mathias","Bastian Leibe"],"abstract":"Tracking in urban street scenes plays a central role in autonomous systems\nsuch as self-driving cars. Most of the current vision-based tracking methods\nperform tracking in the image domain. Other approaches, eg based on LIDAR and\nradar, track purely in 3D. While some vision-based tracking methods invoke 3D\ninformation in parts of their pipeline, and some 3D-based methods utilize\nimage-based information in components of their approach, we propose to use\nimage- and world-space information jointly throughout our method. We present\nour tracking pipeline as a 3D extension of image-based tracking. From enhancing\nthe detections with 3D measurements to the reported positions of every tracked\nobject, we use world-space 3D information at every stage of processing. We\naccomplish this by our novel coupled 2D-3D Kalman filter, combined with a\nconceptually clean and extendable hypothesize-and-select framework. Our\napproach matches the current state-of-the-art on the official KITTI benchmark,\nwhich performs evaluation in the 2D image domain only. Further experiments show\nsignificant improvements in 3D localization precision by enabling our coupled\n2D-3D tracking.","url_abs":"http://arxiv.org/abs/1809.07357v1","url_pdf":"http://arxiv.org/pdf/1809.07357v1.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":[],"tasks":[{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"self-driving-cars","task_name":"Self-Driving Cars"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiple-object-tracking-on-kitti-test-online","task":"Multiple Object Tracking","dataset":"KITTI Test (Online Methods)","model":"CIWT","rank_in_archive_order":32,"of":34,"metrics":{"MOTA":"75.39"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.07357","atlas_url":"https://app.syntology.ai/?focus=1809.07357","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}