Multi-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models
In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.101
Abstract
Multi-target tracking techniques increasingly exploit contextual information about group dynamics. However, approaches established in pedestrian tracking make assumptions about features and motion models which are often inappropriate to sports team tracking, where motion is erratic and players wear similar uniforms with frequent inter-player occlusions. On the other hand, approaches designed specifically for sports team tracking are predominantly aimed at detecting game-state rather than using game-state to enhance individual tracking. We propose a multi-level multi-target sports-team tracker, which overcomes these problems by modelling latent behaviours at both individual and player-pair levels, informed by team-level context dynamics. At the player-level, targets are tracked using adaptive representations, constrained by probabilistic models of player behaviour with respect to collision avoidance. At the team-level, we exploit an adaptive meshing and voting scheme to predict regions of interest, which inform strong motion priors for key individual players. Thus, latent knowledge is derived from team-level contexts to inform player-level tracking. To evaluate our approach, we have developed a new data-set with fully ground-truthed team-sports videos, and demonstrate significantly improved performance over state-of-the-art trackers from the literature.
Session
Poster Session
Files
Extended Abstract (PDF, 1 page, 952K)Paper (PDF, 11 pages, 1.4M)
Bibtex File
Citation
Jingjing Xiao, Rustam Stolkin, and Ales Leonardis. Multi-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
BibTex
@inproceedings{BMVC.28.101
title = {Multi-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models},
author = {Xiao, Jingjing and Stolkin, Rustam and Leonardis, Ales},
year = {2014},
booktitle = {Proceedings of the British Machine Vision Conference},
publisher = {BMVA Press},
editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
doi = { http://dx.doi.org/10.5244/C.28.101 }
}