Depth estimation from disparity of stereo images

The extraction of depth information from stereo image disparities, using a 2-D power cepstrum technique as well as the usual correlation technique, is presented. The edges of the input stereo images were enhanced by a Laplacian of Gaussian (LoG) operator modified for fast implementation. The depth of an object surface is calculated from a simple nonconvergent triangulation technique. The methodology presented in this paper allows a fast yet accurate implementation of computational stereo vision in a machine vision system. The basic concepts of the present paper have been further extended and a motion stereo model has been developed for reconstruction of three-dimensional (3-D) geometry of natural objects using time-sequenced images with capabilities of yielding dense depth maps.