caa a22 4500 467914273 CHVBK 20180406152857.0 cr unu---uuuuu 170328e20060801xx s 000 0 eng 10.1007/s11263-006-6853-9 doi (NATIONALLICENCE)springer-10.1007/s11263-006-6853-9 Contextual Inference in Contour-Based Stereo Correspondence [Elektronische Daten] [Gang Li, Steven Zucker] Standard approaches to stereo correspondence have difficulty when scene structure does not lie in or near the frontal parallel plane, in part because an orientation disparity as well as a positional disparity is introduced. We propose a correspondence algorithm based on differential geometry, that takes explicit advantage of both disparities. The algorithm relates the 2D differential structure (position, tangent, and curvature) of curves in the left and right images to the Frenet approximation of the (3D) space curve. A compatibility function is defined via transport of the Frenet frames, and they are matched by relaxing this compatibility function on overlapping neighborhoods along the curve. The remaining false matches are concurrently eliminated by a model of "near” and "far” neurons derived from neurobiology. Examples on scenes with complex 3D structures are provided. Springer Science + Business Media, LLC, 2006 stereo correspondence nationallicence curve matching nationallicence position disparity nationallicence orientation disparity nationallicence relaxation labeling nationallicence Li Gang Department of Computer Science, Yale University, 06520, New Haven, CT, U.S.A. aut Zucker Steven Department of Computer Science, Yale University, 06520, New Haven, CT, U.S.A. aut International Journal of Computer Vision Kluwer Academic Publishers 69/1(2006-08-01), 59-75 0920-5691 69:1<59 2006 69 11263 https://doi.org/10.1007/s11263-006-6853-9 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-006-6853-9 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Li Gang Department of Computer Science, Yale University, 06520, New Haven, CT, U.S.A aut NATIONALLICENCE 700 1- Zucker Steven Department of Computer Science, Yale University, 06520, New Haven, CT, U.S.A aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 69/1(2006-08-01), 59-75 0920-5691 69:1<59 2006 69 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer