{"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/trajectory-factory-tracklet-cleaving-and-re","title":"Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking","arxiv_id":"1804.04555","date":"2018-04-12","proceeding":null,"authors":["Cong Ma","Changshui Yang","Fan Yang","Yueqing Zhuang","Ziwei Zhang","Huizhu Jia","Xiaodong Xie"],"abstract":"Multi-Object Tracking (MOT) is a challenging task in the complex scene such\nas surveillance and autonomous driving. In this paper, we propose a novel\ntracklet processing method to cleave and re-connect tracklets on crowd or\nlong-term occlusion by Siamese Bi-Gated Recurrent Unit (GRU). The tracklet\ngeneration utilizes object features extracted by CNN and RNN to create the\nhigh-confidence tracklet candidates in sparse scenario. Due to mis-tracking in\nthe generation process, the tracklets from different objects are split into\nseveral sub-tracklets by a bidirectional GRU. After that, a Siamese GRU based\ntracklet re-connection method is applied to link the sub-tracklets which belong\nto the same object to form a whole trajectory. In addition, we extract the\ntracklet images from existing MOT datasets and propose a novel dataset to train\nour networks. The proposed dataset contains more than 95160 pedestrian images.\nIt has 793 different persons in it. On average, there are 120 images for each\nperson with positions and sizes. Experimental results demonstrate the\nadvantages of our model over the state-of-the-art methods on MOT16.","url_abs":"http://arxiv.org/abs/1804.04555v1","url_pdf":"http://arxiv.org/pdf/1804.04555v1.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":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[{"method_slug":"gru","method_name":"GRU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-mot16","task":"Multi-Object Tracking","dataset":"MOT16","model":"GCRA","rank_in_archive_order":21,"of":24,"metrics":{"MOTA":"48.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}