Robust 3-D depth estimation using genetic algorithm in stereo image pairs

In this paper, a genetic algorithm-based optimization technique for stereo matching is proposed. Stereo matching is the essential process for recovering the three-dimensional structure of objects. The geometrical difference of left and right images, called disparity, is constructed as two-dimensional chromosomes with fitness values inversely proportional to their costs. The cost function is composed of the intensity-difference between two images and smoothness of disparity. The crossover and mutation operators in the two-dimensional chromosomes are described. The operations are affected by the disparities of neighbor pixels. The knowledge-augmented operators are shown to result in a rapid convergence and stable result. The genetic algorithm for stereo matching is tested on synthetic and natural images. Experimental results for various images show that the proposed algorithm has good performance even if the image has unfavorable conditions.