{"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/multi-class-multi-object-tracking-using","title":"Multi-Class Multi-Object Tracking using Changing Point Detection","arxiv_id":"1608.08434","date":"2016-08-30","proceeding":null,"authors":["Byungjae Lee","Enkhbayar Erdenee","Songguo Jin","Phill Kyu Rhee"],"abstract":"This paper presents a robust multi-class multi-object tracking (MCMOT)\nformulated by a Bayesian filtering framework. Multi-object tracking for\nunlimited object classes is conducted by combining detection responses and\nchanging point detection (CPD) algorithm. The CPD model is used to observe\nabrupt or abnormal changes due to a drift and an occlusion based spatiotemporal\ncharacteristics of track states. The ensemble of convolutional neural network\n(CNN) based object detector and Lucas-Kanede Tracker (KLT) based motion\ndetector is employed to compute the likelihoods of foreground regions as the\ndetection responses of different object classes. Extensive experiments are\nperformed using lately introduced challenging benchmark videos; ImageNet VID\nand MOT benchmark dataset. The comparison to state-of-the-art video tracking\ntechniques shows very encouraging results.","url_abs":"http://arxiv.org/abs/1608.08434v1","url_pdf":"http://arxiv.org/pdf/1608.08434v1.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":"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiple-object-tracking-on-kitti-test-online","task":"Multiple Object Tracking","dataset":"KITTI Test (Online Methods)","model":"MCMOT-CPD","rank_in_archive_order":27,"of":34,"metrics":{"MOTA":"78.90"},"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}