A general Bayesian algorithm for visual object tracking based on sparse features

This paper describes a Bayesian algorithm for rigid/non-rigid 2D visual object tracking based on sparse image features. The algorithm is inspired by the way human visual cortex segments and tracks different moving objects within its FOV by constructing dynamical nonretinotopic layers. The method is explained as a recursive algorithm between time slices (intra-slice) and as a forward-backward message passing within every time slice (inter-slice) under the Probabilistic Graphical Model (PGM) framework. Finally, an observation model function that resembles the Generalized Hough Transform and allows exploiting internal structure of the problem is employed in order to increase the robustness and accuracy of the algorithm against clutter and missed detections.