• DocumentCode
    3195239
  • Title

    Inferring shape from contour for curved surfaces

  • Author

    Ulupinar, Fatih ; Nevatia, Ramakant

  • Author_Institution
    Inst. for Robotics & Intelligent Systs., Univ. of Southern Calfornia, Los Angeles, CA, USA
  • Volume
    i
  • fYear
    1990
  • fDate
    16-21 Jun 1990
  • Firstpage
    147
  • Abstract
    A technique based on analysis of symmetries in an image is proposed for inferring the 3-D shapes of surfaces of objects in it. This technique is analyzed and applied to zero-Gaussian-curvature surfaces. The method consists of deriving a number of constraints based on a few simple assumptions. The combination of constraints to give unique (or few) solutions is discussed. Experimental results on selected scenes are given and are shown to conform well with human perception
  • Keywords
    pattern recognition; picture processing; 3D shape inferring; curved surfaces; pattern recognition; picture processing; zero-Gaussian-curvature surfaces; Computer vision; Contracts; Equations; Humans; Image analysis; Intelligent robots; Intelligent systems; Layout; Mirrors; Shape;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 1990. Proceedings., 10th International Conference on
  • Conference_Location
    Atlantic City, NJ
  • Print_ISBN
    0-8186-2062-5
  • Type

    conf

  • DOI
    10.1109/ICPR.1990.118080
  • Filename
    118080