A stochastic optimization to dense stereo matching

Abstract

This work presents a general system that achieves an energy minimization-based dense stereo matching through simulated annealing. Dense stereo matching is based on point matching. We show the performance of our approach compared to correlation. We use an optimization method in order to take into consideration the global aspect of the problem, as opposed to the correlation that acts locally on windows, and be able to make this module cooperate with other early vision modules, for instance shape from shading and photometric stereo. The stereo matching problem is an ill-posed problem where the global minimum is hidden by local minima and where the notion of gradient does not exist. For this reason, the simulated annealing algorithm seems the most suitable to solve the stereo matching problem. The constraints of the stereo matching are expressed as an energy functional and elementary transformation.

Keywords: Stereo disparity, stochastic optimization, image matching, constraints, resemblance, epipolar, uniqueness, continuity