Visual Tracking and Dynamic Learning on the Grassmann Manifold with Inference from a Bayesian Framework and State Space Models

We propose a novel visual tracking scheme that exploits boththe geometrical structure of Grassmann manifold and piecewise geodesics under a Bayesian framework. Two particle filters are alternatingly employed on the manifold. One is used for online updating the appearance subspace on the manifold using sliding-window observations, and the other is for tracking moving objects on the manifold based on the dynamic shape and appearance models. Main contributions of the paper include: (a) proposing an online manifold learning strategy by a particle filter, where a mixture of dynamic models is used for both the changes of manifold bases in the tangent plane and the piecewise geodesics on the manifold. (b) proposing a manifold object tracker by incorporating object shape in the tangent plane and the manifold prediction error of object appearance jointly in a particle filter framework. Experiments performed on videos containing significant object pose changes show very robust tracking results. The proposed scheme also shows better performance as comparingwith three existing trackers in terms of tracking drift and the tightness and accuracy of tracked boxes