On-line learning of the transition model for Recursive Bayesian Estimation

Recursive Bayesian Estimation (RBE) is a widespread solution for visual tracking as well as for applications in other domains requiring hidden state estimation. Although theoretically sound and unquestionably powerful, from a practical point of view RBE suffers from the assumption of complete a priori knowledge of the transition model, that is typically unknown. The use of wrong a priori transition model may lead to large estimation errors or even to divergence. This work proposes to prevent these problems, in case of fully observable systems, learning the transition model on-line via Support Vector Regression. An application of this general framework is proposed in the context of linear/Gaussian systems and shown to be superior to a standard, non adaptive solution.