A maximum likelihood stereo algorithm

A maximum likelihood stereo algorithm (1996)

Cached

Download Links

[www.dccia.ua.es]

Other Repositories/Bibliography

DBLP

by Ingemar J. Cox , Sunita L. Hingorani , Satish B. Rao , Bruce M. Maggs

Venue:	Computer Vision and Image Understanding
Citations:	168 - 2 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	A maximum likelihood stereo algorithm	INFERENCE
AUTHOR NAME	Ingemar J. Cox	SVM HeaderParse 0.2
AUTHOR AFFIL	NEC Research Institute	SVM HeaderParse 0.2
AUTHOR ADDR	4 Independence Way; Princeton, NJ 08540	SVM HeaderParse 0.2
AUTHOR NAME	Sunita L. Hingorani	SVM HeaderParse 0.2
AUTHOR AFFIL	NEC Research Institute	SVM HeaderParse 0.2
AUTHOR ADDR	4 Independence Way; Princeton, NJ 08540	SVM HeaderParse 0.2
AUTHOR NAME	Satish B. Rao	SVM HeaderParse 0.2
AUTHOR AFFIL	NEC Research Institute	SVM HeaderParse 0.2
AUTHOR ADDR	4 Independence Way; Princeton, NJ 08540	SVM HeaderParse 0.2
AUTHOR NAME	Bruce M. Maggs	SVM HeaderParse 0.2
AUTHOR AFFIL	School of Computer Science; Carnegie Mellon University	SVM HeaderParse 0.2
AUTHOR ADDR	Pittsburgh, PA 15213	SVM HeaderParse 0.2
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	SVM HeaderParse 0.2
YEAR	1996	INFERENCE
VENUE	Computer Vision and Image Understanding	INFERENCE
VENUE TYPE	JOURNAL	INFERENCE
PAGES	542--567	INFERENCE
VOLUME	63	INFERENCE
CITATIONS	35 found	ParsCit 1.0