Title :
New Robust Matching Cost Functions for Stereo Vision
Author :
El-Mahassni, Edwin D.
Abstract :
An important first step in calculating a disparity map for two stereoscopic images is the estimation of an initial match score. This paper presents two new match score functions, which although constructed from older cost functions perform better across the different lighting conditions listed here, than their predecessors. Error measurements and disparity maps for indoor and outdoor imagery are also presented.
Keywords :
Australia; Computer applications; Computer vision; Cost function; Digital images; Layout; Pixel; Robustness; Stereo vision; Surveillance;
Conference_Titel :
Digital Image Computing Techniques and Applications, 9th Biennial Conference of the Australian Pattern Recognition Society on
Conference_Location :
Glenelg, Australia
Print_ISBN :
0-7695-3067-2
DOI :
10.1109/DICTA.2007.4426789