Using expectation-maximisation to learn dynamical models from visual data

Abstract Tracking with deformable contours in a filtering framework requires a dynamical model for prediction. For any given application, tracking is improved by having an accurate model, learnt from training data. We develop a method for learning dynamical models from training sequences, explicitly taking account of the fact that our data are measurements and not true states. By introducing an ‘augmented-state smoothing filter’, we show how the technique of Expectation-Maximisation can be applied to this problem, and show that the resulting algorithm produces more robust and accurate tracking.