{"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/sparsetrack-multi-object-tracking-by","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","arxiv_id":"2306.05238","date":"2023-06-08","proceeding":null,"authors":["Zelin Liu","Xinggang Wang","Cheng Wang","Wenyu Liu","Xiang Bai"],"abstract":"Exploring robust and efficient association methods has always been an important issue in multiple-object tracking (MOT). Although existing tracking methods have achieved impressive performance, congestion and frequent occlusions still pose challenging problems in multi-object tracking. We reveal that performing sparse decomposition on dense scenes is a crucial step to enhance the performance of associating occluded targets. To this end, we propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets and perform data association on these sparse target subsets in order from near to far. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack. SparseTrack provides a new perspective for solving the challenging crowded scene MOT problem. Only using IoU matching, SparseTrack achieves comparable performance with the state-of-the-art (SOTA) methods on the MOT17 and MOT20 benchmarks. Code and models are publicly available at \\url{https://github.com/hustvl/SparseTrack}.","url_abs":"https://arxiv.org/abs/2306.05238v2","url_pdf":"https://arxiv.org/pdf/2306.05238v2.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":"sparsetrack-multi-object-tracking-by","repo_url":"https://github.com/hustvl/sparsetrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sparsetrack-multi-object-tracking-by","repo_url":"https://github.com/Robotmurlock/Motrack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-dancetrack","task":"Multi-Object Tracking","dataset":"DanceTrack","model":"SparseTrack","rank_in_archive_order":28,"of":37,"metrics":{"AssA":"39.3","DetA":"79.2","HOTA":"55.7","IDF1":"58.1","MOTA":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset":"MOT17","model":"SparseTrack","rank_in_archive_order":8,"of":48,"metrics":{"HOTA":"65.1","IDF1":"80.1","MOTA":"81.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot20-1","task":"Multi-Object Tracking","dataset":"MOT20","model":"SparseTrack","rank_in_archive_order":8,"of":27,"metrics":{"HOTA":"63.4","IDF1":"77.3","MOTA":"78.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.05238","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}