Visual tracking with generative template model based on Riemannian manifold of covariances

Robust visual tracking is a research area that has many important applications. The main challenges include how the target image can be modeled and how this model can be updated. In this paper, we model the target using a covariance descriptor. This descriptor is robust to problems that commonly occur in visual tracking such as pixel-pixel misalignment, pose and illumination changes. We model the changes in the template using a generative process. We introduce a new dynamical model for the template update using a random walk on the Riemannian manifold where the covariance descriptors lie in. This enables us to jointly quantify the uncertainties relating to the kinematic states and the template in a principled way. The sequential inference of the posterior distribution of the kinematic states and the template is done using a particle filter. Our results show that this principled approach is robust to changes in illumination, pose and spatial affine transformation.