Stereo matching using genetic algorithm with adaptive chromosomes

A new stereo matching scheme using a genetic algorithm is presented to impr ove the depth reconstruction method of stereo vision systems. Genetic algor ithms are efficient search methods based on principles of population geneti cs, i.e. mating, chromosome crossover, gene mutation, and natural selection . The proposed approach considers the matching environment as an optimizati on problem and finds the optimal solution by using an evolutionary strategy . Accordingly, genetic operators are adapted for the circumstances of stere o matching: (1) an individual is a disparity set, (2) a chromosome has a 2D structure for handling image signals efficiently, and (3) a fitness functi on is composed of certain constraints which are commonly used in stereo mat ching. Since the fitness function consists of intensity, similarity and dis parity smoothness, the matching and relaxation processes are considered at the same time in each generation. In order to acquire a disparity map consi stent with the image appearance, a region of the input image, divided by ze ro-crossing points, is extracted and used in the determination of the chrom osome shape. As a result, all chromosomes contain the external image form, and the disparity output coincides with the input image without any modific ation of the matching algorithm. In addition, an informed gene generation b ased on intensity difference is applied to reduce the searching space of th e genetic operations, (C) 2001 Pattern Recognition Society. Published by El sevier Science Ltd. All rights reserved.