Learning a probabilistic cellular automaton for people tracking

Abstract

We propose a method for learning a probabilistic cellular automaton from people trajectories and applies the cellular automaton to people tracking in videos. For learning the probabilistic cellular automaton, we introduce dirichlet smoothing to compensate for the lack of the trajectory data because it is difficult to collect the dense and enough data. Furthermore for tracking people, we develop a data assimilation algorithm to sequentially update the probabilistic cellular automaton using the sequence of images. We demonstrate that the proposed probabilistic cellular automaton provides better tracking performance than the existing models.