Skip to main content.

This page’s menu:

Identifying Players in Broadcast Sports Videos using
Conditional Random Fields


The 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011)

Automatic tracking and identification results in a basketball game video.

Abstract
We are interested in the problem of automatic tracking and identification of players in broadcast sport videos shot with a moving camera from a medium distance. While there are many good tracking systems, there are fewer methods that can identify the tracked players. Player identification is challenging in such videos due to blurry facial features (due to fast camera motion and low-resolution) and rarely visible jersey numbers (which, when visible, are deformed due to player movements). We introduce a new system consisting of three components: a robust tracking system, a robust person identification system, and a conditional random field (CRF) model that can perform joint probabilistic inference about the player identities. The resulting system is able to achieve a player recognition accuracy up to 85% on unlabeled NBA basketball clips.
Paper

    PDF (5.0M)
BibTeX
@INPROCEEDINGS{lu_cvpr2011,
     author = {Wei-Lwun Lu and Jo-Anne Ting and Kevin P. Murphy and James J. Little},
     booktitle = {Identifying Players in Broadcast Sports Videos using Conditional Random Fields},
     journal = {Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition},
     year = {2011}
}
Funding

This research is supported in part by

  • National Science and Engineering Research Council of Canada (NSERC)
  • Canadian Institute for Advanced Research (CIAR)
  • GEOIDE Network of Centres of Excellence