Parallelized Robust Multiresolution Motion Estimation

Motion estimation is crucial in domains such as robot vision or image sequence coding. Fast or real time computing is often required but is problematic due to computational complexity. In this paper, an algorithm using multiresolution multigrid Markov random fields will be paralellized. Such realizations have already been studied for fine parallelizations on massively parallel machines. The goal of this paper is to achieve a coarse parallelization on a network of workstations, using PVM. 1. INTRODUCTION Many techniques have already been proposed for motion analysis of image sequences [6, 8]. This paper will focus interest on global energy function based motion estimation algorithm. The general issue is to find the global minimum of an objective (also called energy) function describing the interaction between observation variables which correspond to the representation of the observed data and hidden variables which are the information to be extracted from the original images. Standard..