• DocumentCode
    3207314
  • Title

    Recovering LSHGCs and SHGCs from stereo

  • Author

    Chung, Ronald C K ; Nevatia, Ramakant

  • Author_Institution
    Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
  • fYear
    1992
  • fDate
    15-18 Jun 1992
  • Firstpage
    42
  • Lastpage
    48
  • Abstract
    The problem of computing volumetric shape from stereo is examined. It is argued that intermediate two-and-one-half-dimensional dense or wire-frame descriptions may not be always possible from stereo, especially when there are curved surfaces in the scene, and that 3D volumetric descriptions of objects may have to be derived directly from stereo correspondences. Methods are then presented for recovering volumetric shape with linear straight homogeneous generalized cones (LSHGCs) and straight homogeneous generalized cones (SHGCs) as the shape models, using some invariant properties in their monocular and stereo projections. Experimental results on images of objects with curved surfaces are given
  • Keywords
    computational geometry; computer vision; stereo image processing; 3D volumetric descriptions; curved surfaces; linear straight homogeneous generalized cones; shape models; stereo correspondences; volumetric shape from stereo; Computer science; Image recognition; Image segmentation; Indexing; Intelligent robots; Intelligent systems; Interpolation; Layout; Shape measurement; Surface texture;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 1992. Proceedings CVPR '92., 1992 IEEE Computer Society Conference on
  • Conference_Location
    Champaign, IL
  • ISSN
    1063-6919
  • Print_ISBN
    0-8186-2855-3
  • Type

    conf

  • DOI
    10.1109/CVPR.1992.223229
  • Filename
    223229