Stereo disparity estimation using GA-controlled search in the DCT domain

The objective of stereo matching is, given a point in one view of a scene, to find the identical point in another view from an adjacent camera. This article demonstrates the use of the discrete cosine transform (DCT) with a genetic algorithm (GA) to perform the stereo matching process. The matching process is implemented by generating for each image block sets of estimated DCT coefficients which when reverse transformed become the estimated disparity map for that block. The job of optimising the DCT coefficients is carried out by the GA. A review of stereo vision and genetic algorithms is given