{"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/motchallenge-2015-towards-a-benchmark-for","title":"MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking","arxiv_id":"1504.01942","date":"2015-04-08","proceeding":null,"authors":["Laura Leal-Taixé","Anton Milan","Ian Reid","Stefan Roth","Konrad Schindler"],"abstract":"In the recent past, the computer vision community has developed centralized\nbenchmarks for the performance evaluation of a variety of tasks, including\ngeneric object and pedestrian detection, 3D reconstruction, optical flow,\nsingle-object short-term tracking, and stereo estimation. Despite potential\npitfalls of such benchmarks, they have proved to be extremely helpful to\nadvance the state of the art in the respective area. Interestingly, there has\nbeen rather limited work on the standardization of quantitative benchmarks for\nmultiple target tracking. One of the few exceptions is the well-known PETS\ndataset, targeted primarily at surveillance applications. Despite being widely\nused, it is often applied inconsistently, for example involving using different\nsubsets of the available data, different ways of training the models, or\ndiffering evaluation scripts. This paper describes our work toward a novel\nmultiple object tracking benchmark aimed to address such issues. We discuss the\nchallenges of creating such a framework, collecting existing and new data,\ngathering state-of-the-art methods to be tested on the datasets, and finally\ncreating a unified evaluation system. With MOTChallenge we aim to pave the way\ntoward a unified evaluation framework for a more meaningful quantification of\nmulti-target tracking.","url_abs":"http://arxiv.org/abs/1504.01942v1","url_pdf":"http://arxiv.org/pdf/1504.01942v1.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":"motchallenge-2015-towards-a-benchmark-for","repo_url":"https://github.com/guoxixu/TrafficFlowTracking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"motchallenge-2015-towards-a-benchmark-for","repo_url":"https://github.com/khalidw/MOT16_Annotator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[],"datasets_introduced":[{"slug":"mot15","name":"MOT15","full_name":"Multiple Object Tracking 15"},{"slug":"motchallenge","name":"MOTChallenge","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1504.01942","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}