Title
Intensity- and Gradient-Based Stereo Matching Using Hierarchical Gaussian Basis Functions
Abstract
In this paper, we propose a stereo correspondence method by minimizing intensity and gradient errors simultaneously. In contrast to conventional use of image gradients, the gradients are applied in the deformed image space. Although a uniform smoothness constraint is imposed, it is applied only to nonfeature regions. To avoid local minima in the function minimization, we propose to parameterize the disparity function by hierarchical Gaussians. Both the uniqueness and the ordering constraints can be easily imposed in our minimization framework. Besides, we propose a method to estimate the disparity map and the camera response difference parameters simultaneously. Experiments with various real stereo images show robust performances of our algorithm.
Year
DOI
Venue
1998
10.1109/34.730551
IEEE Trans. Pattern Anal. Mach. Intell.
Keywords
Field
DocType
hierarchical gaussian basis functions,various real stereo image,stereo correspondence method,gradient-based stereo matching,disparity map,minimization framework,image space,camera response difference parameter,function minimization,disparity function,image gradient,conventional use,scale space,local minima,stochastic processes,deformation,interpolation,stereo vision,parameter estimation,robustness,machine vision,pixel,minimisation
Computer vision,Pattern recognition,Computer science,Scale space,Maxima and minima,Minification,Gaussian,Minimisation (psychology),Artificial intelligence,Basis function,Estimation theory,Smoothness
Journal
Volume
Issue
ISSN
20
11
0162-8828
Citations 
PageRank 
References 
46
3.00
36
Authors
3
Name
Order
Citations
PageRank
Guo-Qing Wei134667.34
Wilfried Brauer2969299.36
gerd hirzinger35185617.40