Parallelization of belief propagation method on embedded multicore processors for stereo vision

Abstract

Markov random field models provide a robust formulation of low-level vision problems. Among the problems, stereo vision remains the most investigated field. The belief propagation provides accurate result in stereo vision problems, however, the algorithm remains slow for practical use. In this paper we examine and extract the parallelisms in the belief propagation method for stereo vision on multicore processors. The results show that with parallelization exploration on multi-core processors, the belief propagation algorithm can have a 13.5 times speedup compared to the single processor implementation. The experimental results also indicate that the parallelized belief propagation algorithm on multicore processors is able to provide a frame rate in 6 frames per second.