From an intensity image to 3-D segmented descriptions

  • Mourad Zerroug
  • Ramakant Nevatia
Geometric and Topological Representations
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1144)


We address the inference of 3-D segmented descriptions of complex objects from a single intensity image. Our approach is based on the analysis of the projective properties of a small number of generalized cylinder primitives and their relationships in the image which make up common man-made objects. Past work on this problem has either assumed perfect contours as input or used 2-dimensional shape primitives without relating them to 3-D shape. The method we present explicitly uses the 3-dimensionality of the desired descriptions and directly addresses the segmentation problem in the presence of contour breaks, markings shadows and occlusion. This work has many significant applications including recognition of complex curved objects from a single real intensity image. We demonstrate our method on real images.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    R. Bergevin and M.D. Levine, “Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings,” in IEEE Transactions PAMI, 15, pages 19–36, 1993.Google Scholar
  2. [2]
    P.J. Besl and R.C. Jain, “Segmentation Through Symbolic Surface Descriptions”, In Proceedings of IEEE CVPR, pages 77–85, 1986.Google Scholar
  3. [3]
    I. Biederman, “Recognition by Components: A Theory of Human Image Understanding”, Psychological Review, 94(2):115–147.Google Scholar
  4. [4]
    T.O. Binford, “Visual Perception by Computer,” IEEE Conference on Systems and Controls, December 1971, Miami.Google Scholar
  5. [5]
    T.O. Binford, “Inferring Surfaces from Images,” Artificial Intelligence, 17:205–245, 1981.CrossRefGoogle Scholar
  6. [6]
    S. Dickinson, “3-D shape Recovery using Distributed Aspect Matching,” IEEE Transactions PAMI, 14(2):174–198, 1992.Google Scholar
  7. [7]
    Do Carmo, “Differential Geometry of Curves and Surfaces,” Prentice Hall, 1976.Google Scholar
  8. [8]
    T.J. Fan, G. Medioni and R. Nevatia, “Recognizing 3-D Objects using Surface Descriptions”, IEEE Transactions PAMI, 11(11):1140–1157, 1989.Google Scholar
  9. [9]
    A. Gross and T. Boult, “Recovery of Generalized Cylinders from a Single Intensity View”, In Proc. Image Understanding Workshop, pages 557–564, 1990.Google Scholar
  10. [10]
    J.E. Hummel and I. Biederman, “Dynamic Binding in a Neural Network for Shape Recognition” Psychological Review, 1992.Google Scholar
  11. [11]
    J. Malik,“Interpreting line drawings of curved objects,” International Journal of Computer Vision, 1(1):73–103, 1987.CrossRefGoogle Scholar
  12. [12]
    D. Marr, “Vision”, W.H. Freeman and Co. Publishers, 1981Google Scholar
  13. [13]
    R. Mohan and R. Nevatia, “Perceptual organization for scene segmentation”, IEEE Transactions PAMI. 1992.Google Scholar
  14. [14]
    V. Nalwa, “Line drawing interpretation: Bilateral symmetry,” IEEE Transactions PAMI, 11:1117–1120, 1989.Google Scholar
  15. [15]
    R. Nevatia and T.O. Binford, “Description and recognition of complex curved objects,” Artificial Intelligence, 8(1):77–98, 1977.Google Scholar
  16. [16]
    A. Pentland, “Recognition by Parts,” in Proceedings of the ICCV, pages 612–620, 1987.Google Scholar
  17. [17]
    K. Rao and R. Nevatia, “Description of complex objects from incomplete and imperfect data,” In Proceedings of the Image Understanding Workshop, pages 399–414, Palo Alto, California, May 1989.Google Scholar
  18. [18]
    L. Roberts, “Machine Perception of Three-Dimensional Solids,” MIT Press, 1965.Google Scholar
  19. [19]
    H. Sato and T.O. Binford, “Finding and recovering SHGC objects in an edge image,” Computer Vision Graphics and Image Processing, 57(3), pages 346–356, 1993.Google Scholar
  20. [20]
    F. Ulupinar and R. Nevatia, “Shape from contours: SHGCs,” In Proceedings of ICCV, pages 582–582, Osaka, Japan, 1990.Google Scholar
  21. [21]
    F. Ulupinar and R. Nevatia, “Recovering Shape from Contour for Constant Cross Section Generalized Cylinders,” In Proceedings of Computer Vision and Pattern Recognition, pages 674–676. 1991. Maui, Hawaii.Google Scholar
  22. [22]
    F. Ulupinar and R. Nevatia, “Perception of 3-D surfaces from 2-D contours,” IEEE Transactions PAMI, pages 3–18, 15, 1993.Google Scholar
  23. [23]
    M. Zerroug and R. Nevatia, “Quasi-invariant properties and 3D shape recovery of nonstraight, non-constant generalized cylinders”, In Proceedings of IEEE CVPR, pages 96–103, New York, 1993.Google Scholar
  24. [24]
    M. Zerroug and R. Nevatia, “Using invariance and quasi-invariance for the segmentation and recovery of curved objects,” in Proceedings of the 2nd ARPA/ESPRIT Workshop on Geometric Invariance in Computer Vision, The Azores, 1993.Google Scholar
  25. [25]
    M. Zerroug and R. Nevatia, “Segmentation and 3-D recovery of SHGCs from a single intensity image”, European Conference on Computer Vision, Stockholm, 1994.Google Scholar
  26. [26]
    M. Zerroug and R. Nevatia, “Volumetric Descriptions from a Single Intensity Image,” to appear in the International Journal of Computer Vision.Google Scholar
  27. [27]
    M. Zerroug and R. Nevatia, “Segmentation and 3-D recovery of curved axis generalized cylinders from an intensity image”, Proceedings of the ICPR, Jerusalem 1994.Google Scholar
  28. [28]
    Mourad Zerroug. “Segmentation and Inference of 3-D Descriptions from an Intensity Image”. Ph.D. dissertation, Institute for Robotics and Intelligent Systems, University of Southern California, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Mourad Zerroug
    • 1
  • Ramakant Nevatia
    • 1
  1. 1.Institute for Robotics and Intelligent SystemsUniversity of Southern CaliforniaLos Angeles

Personalised recommendations