Title :
On the derivation of geometric constraints in stereo
Author :
Stewart, Charles V.
Author_Institution :
Dept. of Comput. Sci., Rensselaer Polytech. Inst., Troy, NY, USA
Abstract :
Probability density functions (PDFs) are derived for many of the geometric measurements upon which stereo matching techniques are based, including orientation differences between matching line segments or curves, the gradient of disparity, the directional derivative of disparity, and disparity differences between matches. The PDFs resulting from the transformations are used to critically examine many existing stereo techniques. Several techniques based on these PDFs are proposed
Keywords :
computational geometry; image recognition; probability; stereo image processing; PDFs; curves; directional derivative; disparity; disparity differences; geometric constraints; geometric measurements; line segments; orientation differences; probability density functions; stereo matching techniques; Cameras; Computer science; Geometry; Image segmentation; Jacobian matrices; Layout; Measurement uncertainty; Probability density function; Robotics and automation; Solid modeling;
Conference_Titel :
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
Conference_Location :
Champaign, IL
Print_ISBN :
0-8186-2855-3
DOI :
10.1109/CVPR.1992.223177