Title :
Non-isotropic regularization of the correspondence space in stereo-vision
Author :
Ben-Ari, Rami ; Sochen, Nir
Author_Institution :
Dept. of Appl. Sci., Tel Aviv Univ., Israel
Abstract :
The correspondence problem in stereo vision is notoriously difficult. In many approaches a noisy solution is extracted from the correspondence space. Various sophisticated regularization techniques are applied then on this noisy solution. We study here the possibility to denoise the correspondence/correlation space before extracting the solution, by a non-linear and non-isotropic scheme. We show that this method preserves edges (depth discontinuities) well and overcomes some of the problems encountered in previous approaches.
Keywords :
correlation methods; feature extraction; image denoising; stereo image processing; correlation space; correspondence space; image denoising; nonisotropic regularization; sophisticated regularization techniques; stereo-vision; Area measurement; Cameras; Convolution; Cost function; Energy resolution; Focusing; Gaussian noise; Layout; Mathematics; Stereo vision;
Conference_Titel :
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
Print_ISBN :
0-7695-2128-2
DOI :
10.1109/ICPR.2004.1333761