Motion Segmentation Using Inference in Dynamic Bayesian Networks

Existing formulations for optical flow estimation and image segmentation have used Bayesian Networks and Markov Random Field (MRF) priors to impose smoothness of segmentation. These approaches typically focus on estimation in a single time slice based on two consecutive images. We develop a motion segmentation framework for a continuous stream of images using inference in a corresponding Dynamic Bayesian Network (DBN) formulation. It realises a spatio-temporal integration of optical flow and segmentation information using a transition prior that incorporates spatial and temporal coherence constraints on the flow field and segmentation evolution. The main contribution is the embedding of these particular assumptions into a DBN formulation and the derivation of a computationally efficient two-filter inference method based on factored belief propagation (BP) that allows for onand offline parameter optimisation. The spatio-temporal coupling implemented in the transition priors ensures smooth flow field and segmentation estimates without using MRFs. The algorithm is tested on synthetic and real image sequences.