Visual tracking via particle filtering on the affine group

We propose a particle filtering-based visual tracker, in which the affine group is treated as the state. We first develop a general particle filtering algorithm that explicitly takes into account the geometry of the affine group. The tracking performance is further enhanced by the geometric auto-regressive process used for the state dynamics, combined state-covariance estimation, and robust measurement likelihood calculation using the incremental principal geodesic analysis of the image covariance descriptors. The feasibility of our proposed visual tracker is demonstrated via experimental studies.