DMCA
A maximum likelihood stereo algorithm (1996)
| Venue: | Computer Vision and Image Understanding |
| Citations: | 234 - 2 self |
BibTeX
@ARTICLE{Cox96amaximum,
author = {Ingemar J. Cox and Sunita L. Hingorani and Satish B. Rao and Bruce M. Maggs},
title = {A maximum likelihood stereo algorithm},
journal = {Computer Vision and Image Understanding},
year = {1996},
volume = {63},
pages = {542--567}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A stereo algorithm is presented that optimizes a maximum likelihood cost function. The maximum likelihood cost function assumes that corresponding features in the left and right images are Normally distributed about a common true value and consists of a weighted squared error term if two features are matched or a ( xed) cost if a feature is determined to be occluded. The stereo algorithm nds the set of correspondences that maximize the cost function subject to ordering and uniqueness constraints. The stereo algorithm is independent of the matching primitives. However, for the experiments described in this paper, matching is performed on the individual pixel intensities. Contrary to popular belief, the pixel-based stereo appears to be robust for a variety of images. It also has the advantages of (i) providing a dense disparity map, (ii) requiring no feature extraction and (iii) avoiding the adaptive windowing problem of area-based correlation methods. Because feature extraction and windowing are unnecessary, avery fast implementation is possible. Experimental results reveal that good stereo correspondences can be found using only ordering and uniqueness constraints, i.e. without local smoothness constraints. However, it is shown that the original maximum likelihood stereo algorithm exhibits multiple global minima. The dynamic programming algorithm is guaranteed to nd one, but not necessarily the same one for each epipolar scanline causing erroneous
Keyphrases
maximum likelihood stereo algorithm stereo algorithm feature extraction uniqueness constraint maximum likelihood cost function dense disparity map individual pixel intensity weighted squared error term area-based correlation method local smoothness constraint adaptive windowing problem epipolar scanline common true value popular belief right image dynamic programming algorithm matching primitive pixel-based stereo cost function subject multiple global minimum good stereo correspondence experimental result avery fast implementation original maximum likelihood stereo algorithm
