New development of stereo vision  

作　　者：许传祥 石青云 程民德 

机构地区：[1]Information Saenoe Center, Peking University, Beijing 100871, China

出　　处：《Chinese Science Bulletin》1996年第11期949-953,共5页

基　　金：Project supported by the National Natural Science Foundation of China.

摘　　要：To derive accurate three-dimensional (3-D) information of a scene is an important pur-pose in computer vision. Two-viempoints stereo vision (we will call it stereo vision in thefollowing) is a technique for reconstructing the 3--D description of a scene from the imagesobserved from two viewpoints. The main procedure in stereo vision is: (i) define and ex-tract the primitives in images; (ii) find the correspondence of these primitives between

关 键 词：STEREO VISION EDGE CONTOUR LINES Wu’s method. 

分 类 号：TN873[电子电信—信息与通信工程]