Segmentation and recovery of SHGCs from a real intensity image

  • Mourad Zerroug
  • Ramakant Nevatia
Shape Modelling
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)


We address the problem of scene segmentation and shape recovery from a single real intensity image. Solving this problem is central to obtaining 3-D scene descriptions in realistic applications where perfect data cannot be obtained and only one image is available. The method we propose addresses a large class of generic shapes, namely straight homogeneous generalized cylinders (SHGCs). It consists of the derivation and use of their geometric projective properties in a multi-level grouping approach. We describe an implemented and working system that detects and recovers full SHGC descriptions in the presence of image imperfections such as broken contours, surface markings, shadows and occlusion. We demonstrate our method on complex 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]
    I. Biederman, “Recognition by components: A theory of human image understanding”, Psychological Review, 94(2):115–147.Google Scholar
  3. [3]
    T.O. Binford, “Visual perception by computer,” IEEE Conference on Systems and Controls, December 1971, Miami.Google Scholar
  4. [4]
    T.O. Binford, “Inferring surfaces from images,” Artificial Intelligence, 17:205–245, 1981.Google Scholar
  5. [5]
    R.A. Brooks, “Model-based three dimensional interpretation of two dimensional images,” IEEE Transactions PAMI, 5(2):140–150, 1983.Google Scholar
  6. [6]
    M. Dhome, R. Glachet and J.T. Lapreste, “Recovering the scaling function of a SHGC from a single perspective view”, In Proceedings of IEEE CVPR, pages 36–41, 1992.Google Scholar
  7. [7]
    A. Gross and T. Boult, “Recovery of generalized cylinders from a single intensity view,” In Proceedings of the Image Understanding Workshop, pages 557–564, Pennsylvania, 1990.Google Scholar
  8. [8]
    J. Liu, J. Mundy, D. Forsyth, A. Zisserman and C. Rothwell, “Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders,” In Proceedings of IEEE CVPR, pages 123–128, 1993.Google Scholar
  9. [9]
    R. Mohan and R. Nevatia, “Perceptual organization for scene segmentation”, IEEE Transactions PAMI. 1992.Google Scholar
  10. [10]
    T. Nakamura, M. Asada and Y. Shirai, “A qualitative approach to quantitative recovery of SHGC's shape and pose from shading and contour”, In Proceedings of IEEE CVPR, pages 116–121, New York, 1993.Google Scholar
  11. [11]
    V. Nalwa, “Line drawing interpretation: Bilateral symmetry,” IEEE Transactions PAMI, 11:1117–1120, 1989.Google Scholar
  12. [12]
    R. Nevatia and T.O. Binford, “Description and recognition of complex curved objects,” Artificial Intelligence, 8(1):77–98, 1977.Google Scholar
  13. [13]
    R. Nevatia, K. Price and G. Medioni, “USC image understanding research: 1990–1991”. In Proceedings of the Image Understanding Workshop, San Diego, California, 1991.Google Scholar
  14. [14]
    J. Ponce, D Chelberg and W.B. Mann, “Invariant properties of straight homogeneous generalized cylinders and their contours,” IEEE Transactions PAMI, 11(9):951–966, 1989.Google Scholar
  15. [15]
    E. 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
  16. [16]
    M. Richetin, M. Dhome, J.T. Lapestre and G. Rives, “Inverse Perspective Transform Using Zero-Curvature Contours Points: Applications to the Localization of Some Generalized Cylinders from a Single View,” IEEE Transactions PAMI, 13(2):185–192, 1991.Google Scholar
  17. [17]
    C.A. Rothwell, D.A. Forsyth, A. Zisserman and J.L Mundy, “Extracting projective structure from single perspective views of 3D point sets”, in the proceedings of the ICCV, pages 573–582, Berlin, Germany. 1993.Google Scholar
  18. [18]
    P. Saint-Marc and G. Medioni, “B-spline contour representation and symmetry detection,” In First ECCV, pages 604–606, Antibes, France, April 1990.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]
    S.A. Shafer and T. Kanade, “The theory of straight homogeneous generalized cylinders,” Technical Report CS-083-105, Carnegie Mellon University, 1983.Google Scholar
  21. [21]
    F. Ulupinar and R. Nevatia, “Shape from contours: SHGCs,” In Proceedings of ICCV, pages 582–582, Osaka, Japan, 1990.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 International Workshop on geometric invariance in computer vision, The Azores, 1993.Google Scholar
  25. [25]
    M. Zerroug and R. Nevatia, “Volumetric descriptions from a single intensity image,” to appear in IJCV.Google Scholar

Copyright information

© Springer-Verlag 1994

Authors and Affiliations

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

Personalised recommendations