Model field particles with positional appearance learning for sports player tracking
Tracking multiple players is crucial to analyzing sports videos in real time. Yet, illumination variations, background clutter, frequent occlusions among players who look similar in low-resolution, and non-linear motion patterns of the targets make sports player tracking di cult. Particle- ltering based approaches have been utilized for their ability in tracking under occlusion and rapid motions. Unlike the common practice of choosing particles on targets, we introduce the notion of shared particles densely sampled at xed positions on the model eld. Likelihoods of being on di erent particles are calculated for the targets using the proposed combined appearance and motion model. After globally distributing particles among the tracks, particles are weighted using an appearance model with a player detection score, and the track locations are updated by the weighted combination of the particles. This enables encapsulating the interactions among the targets in the state-space model and tracking players through challenging occlusions. We further introduce collective motion model and positional appearance learning to recover lost players and detect identity switches among the tracks. The proposed algorithm is embedded into a real player tracking system. Complete steps of the system are described and the proposed approach is evaluated on large-scale video. Experimental results show that the proposed tracker performs better than standard particle ltering and the state-of-the-art single-object trackers by losing less number of tracks and preserving more identities. Moreover, the proposed approach achieves a higher tracking accuracy with lower error rates on a publicly available soccer tracking dataset when compared to the previous methods.