Accomplishments and challenges of computer stereo vision

Segmentation and grouping of image elements is required to proceed with image recognition. Due to the fact that the images are two dimensional (2D) representations of the real three dimensional (3D) scenes, the information of the third dimension, like geometrical relations between the objects that are important for reasonable segmentation and grouping, are lost in 2D image representations. Computer stereo vision implies on understanding information stored in 3D-scene. Techniques for stereo computation are observed in this paper. The methods for solving the correspondence problem in stereo image matching are presented. The process of 3D-scene reconstruction from stereo image pairs and extraction of parameters important for image understanding are described. Occluded and surrounding areas in stereo image pairs are stressed out as important for image understanding.