A Direct Disparity Estimation Technique for Depth Segmentation
Atsuto Maki, Tomas Uhlin, Jan‐Olof Eklundh · 1996
: This paper concerns acquisition of dense depth maps in the context of image segmentation, which is fundamental in various vision applications. Focusing on stereoscopic vision as the methodology, our goal here is to develop a scheme which is computationally simple but still allows a dense disparity map. For the estimation of stereo disparity, for this reason, we employ an approach based on local Fourier phase obtained by complex bandpass filters. We consider the characteristics of this search-free and thus fast approach as suitable to compute stereo disparity as a basic cue for image segmentation. Within the framework of the phase-based algorithm, in this paper, two issues are discussed. One is the use of the derivative-based filters, and the other is the certainty-weighted disparity propagation. Keywords: disparity, depth segmentation, phase-based algorithm, complex filters, disparity propagation 1 Introduction While different image features such as motion, color, or edge informat...