Issue No. 03 - March (1998 vol. 20)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.667890
<p><b>Abstract</b>—We propose a representation of images, called <it>intrinsic curves</it>, that transforms stereo matching from a search problem into a nearest-neighbor problem. Intrinsic curves are the paths that a set of local image descriptors trace as an image scanline is traversed from left to right. Intrinsic curves are ideally invariant with respect to disparity. Stereo correspondence then becomes a trivial lookup problem in the ideal case. We also show how to use intrinsic curves to match real images in the presence of noise, brightness bias, contrast fluctuations, moderate geometric distortion, image ambiguity, and occlusions. In this case, matching becomes a nearest-neighbor problem, even for very large disparity values.</p>
Stereo vision, stereo matching, correspondence problem, disparity, ambiguity, occlusions, search, nearest-neighbor search, dynamic programming.
R. Manduchi and C. Tomasi, "Stereo Matching as a Nearest-Neighbor Problem," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 20, no. , pp. 333-340, 1998.