Tracking When The Camera Looks Away
Keywords
Analytical models; Cameras; Computer vision; Games; Tracking; TV; Videos
Abstract
Tracking players in sports videos presents numerous challenges due to weak distinguishing features and unpredictable motion. Considerable work has been done to track players in such videos using a combination of appearance and motion modeling, mostly in continuous streams of video. However, in a broadcast sports video, having advertisements, replays and intermittent change of camera view, it becomes a challenging task to keep track of players over an entire game. In this work, we solve a novel problem of tracking over a sequence of temporally disjoint soccer videos without the use of appearance cue, using a Graph based optimization approach. Each team is represented by a graph, in which the nodes correspond to player positions and the edge weights depend on spatial inter-player distance. We use team formation to associate tracks between clips and provide an end-to-end system that is able to perform statistical and tactical analysis of the game. We also introduce a new challenging dataset of an international soccer game.
Publication Date
2-11-2016
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Volume
2016-February
Number of Pages
742-750
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICCVW.2015.101
Copyright Status
Unknown
Socpus ID
84961990989 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84961990989
STARS Citation
Soomro, Khurram; Khokhar, Salman; and Shah, Mubarak, "Tracking When The Camera Looks Away" (2016). Scopus Export 2015-2019. 4520.
https://stars.library.ucf.edu/scopus2015/4520