Title :
Correspondence stereo vision under general stereo camera configuration
Author_Institution :
Dept. of Autom. & Comput. Eng., Chinese Univ. of Hong Kong, Shatin, China
Abstract :
Despite extensive study on it for decades, stereo vision is still widely regarded as a difficult problem. What makes it difficult is the stereo correspondence problem. Earlier Aloimonos and Herve (1992) proposed an algorithm that avoids the need of establishing correspondences across the stereo images. The algorithm however assumes a particular stereo configuration: the parallel-axes stereo geometry. This paper describes how the restriction could be removed and provides, in a closed-form format, an extension of the algorithm for general stereo geometry.
Keywords :
cameras; geometry; stereo image processing; closed-form format; correspondence stereo vision; general stereo camera configuration; parallel-axes stereo geometry; stereo images; Automation; Cameras; Computer vision; Equations; Geometrical optics; Information geometry; Layout; Stereo vision;
Conference_Titel :
Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003 IEEE International Conference on
Print_ISBN :
0-7803-7925-X
DOI :
10.1109/RISSP.2003.1285608