This paper presents a method to create a panorama disparity map of a natural environment from stereo images captured by our original multi-purpose 3-camera panorama capturing system which features accurate frame synchronization between 3 channels and can be used outdoors through battery operation. For robust determination of correspondences of a stereo pair, we make use of a census transform, a kind of non-parametric local transform. The census transform summarizes local image structure as a bit string, and gives very good stereo-matching results without such processes as image pyramids, bi-directional search, complicated matching evaluation, and too much edge detection dependent interpolation. To interpolate unknown disparities, we introduced a process influenced by the K-means algorithm. Then, use of 3-channel images and overlapping of the maps give multiple disparity values for one pixel, which enables screening of very confident values. We have obtained very good results on such complex scenes as contain branches and leaves of trees.
[1]
Ramin Zabih,et al.
Non-parametric Local Transforms for Computing Visual Correspondence
,
1994,
ECCV.
[2]
Gérard G. Medioni,et al.
3-D Surface Description from Binocular Stereo
,
1992,
IEEE Trans. Pattern Anal. Mach. Intell..
[3]
Takeshi Naemura,et al.
Multi-media ambiance communication based on actual moving pictures
,
1999,
Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).
[4]
Takeshi Naemura,et al.
Multimedia ambience communication based on actual moving pictures in a steroscopic projection display environment
,
2000,
Electronic Imaging.
[5]
Takeshi Naemura,et al.
High-quality stereo panorama generation using a three-camera system
,
2000,
Visual Communications and Image Processing.
[6]
Mohammed Bennamoun,et al.
A hybrid stereo matching algorithm incorporating the rank constraint
,
1999
.