A Multiple Hypothesis Approach to Figure Tracking

This paper describes a probabilistic multiple-hypothesis framework for tracking highly articulated objects. In this framework, the probability density of the tracker state is represented as a set of modes with piecewise Gaussians characterizing the neighborhood around these modes. The temporal evolution of the probability density is achieved through sampling from the prior distribution, followed by local optimization of the sample positions to obtain updated modes. The multimodal nature of this representation endows significantly greater robustness when tracking through ambiguous events than a unimodal tracker. The quasi-parametric form of the model is suited for highdimensional state-spaces which cannot be efficiently modeled using a non-parametric approach. Results are shown for tracking Fred Astaire in a movie dance sequence.