Abstract

We employ hierarchical data association to track players in team sports. Player movements are often complex and highly correlated with both nearby and distant players. A single model would require many degrees of freedom to represent the full motion diversity and could be diffificult to use in practice. Instead, we introduce a set of Game Context Features extracted from noisy detections to describe the current state of the match, such as how the players are spatially distributed. Our assumption is that players react to the current situation in only a fifinite number of ways. As a result, we are able to select an appropriate simplifified affifinity model for each player and time instant using a random decision forest based on current track and game context features. Our context-conditioned motion models implicitly incorporate complex inter-object correlations while remaining tractable. We demonstrate signifificant performance improvements over existing multi-target tracking algorithms on basketball and fifield hockey sequences several minutes in duration and containing 10 and 20 players respectively