{"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/lifting-multi-view-detection-and-tracking-to","title":"Lifting Multi-View Detection and Tracking to the Bird's Eye View","arxiv_id":"2403.12573","date":"2024-03-19","proceeding":null,"authors":["Torben Teepe","Philipp Wolters","Johannes Gilg","Fabian Herzog","Gerhard Rigoll"],"abstract":"Taking advantage of multi-view aggregation presents a promising solution to tackle challenges such as occlusion and missed detection in multi-object tracking and detection. Recent advancements in multi-view detection and 3D object recognition have significantly improved performance by strategically projecting all views onto the ground plane and conducting detection analysis from a Bird's Eye View. In this paper, we compare modern lifting methods, both parameter-free and parameterized, to multi-view aggregation. Additionally, we present an architecture that aggregates the features of multiple times steps to learn robust detection and combines appearance- and motion-based cues for tracking. Most current tracking approaches either focus on pedestrians or vehicles. In our work, we combine both branches and add new challenges to multi-view detection with cross-scene setups. Our method generalizes to three public datasets across two domains: (1) pedestrian: Wildtrack and MultiviewX, and (2) roadside perception: Synthehicle, achieving state-of-the-art performance in detection and tracking. https://github.com/tteepe/TrackTacular","url_abs":"https://arxiv.org/abs/2403.12573v1","url_pdf":"https://arxiv.org/pdf/2403.12573v1.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":"lifting-multi-view-detection-and-tracking-to","repo_url":"https://github.com/tteepe/tracktacular","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-recognition","task_name":"3D Object Recognition"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multiview-detection","task_name":"Multiview Detection"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":null,"task_name":"multi-view detection"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-multiviewx","task":"Multi-Object Tracking","dataset":"MultiviewX","model":"TrackTacular (Bilinear Sampling)","rank_in_archive_order":1,"of":2,"metrics":{"IDF1":"85.6","MOTA":"92.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-wildtrack","task":"Multi-Object Tracking","dataset":"Wildtrack","model":"TrackTacular (Bilinear Sampling)","rank_in_archive_order":2,"of":9,"metrics":{"IDF1":"95.3","MOTA":"91.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-multiviewx","task":"Multiview Detection","dataset":"MultiviewX","model":"TrackTacular (Bilinear Sampling)","rank_in_archive_order":2,"of":9,"metrics":{"MODA":"96.5","MODP":"75.0","Recall":"97.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-wildtrack","task":"Multiview Detection","dataset":"Wildtrack","model":"TrackTacular (Depth Splatting)","rank_in_archive_order":3,"of":10,"metrics":{"MODA":"93.2","MODP":"77.5","Recall":"95.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.12573","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}