CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 1998 vol.20 Issue No.11 - November
Issue No.11 - November (1998 vol.20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.730551
<p><b>Abstract</b>—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 <it>deformed</it> 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.</p>
Stereo matching, intensity values, intensity gradients, deformation, scale-space, hierarchical Gaussians, ordering constraint, stochastic gradients, response difference compensation.
Guo-Qing Wei, Gerd Hirzinger, "Intensity- and Gradient-Based Stereo Matching Using Hierarchical Gaussian Basis Functions", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.20, no. 11, pp. 1143-1160, November 1998, doi:10.1109/34.730551