Advertisement

Duals, Invariants, and the Recognition of Smooth Objects from Their Occluding Contour

  • David Renaudie
  • David Kriegman
  • Jean Ponce
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1842)

Abstract

This paper presents a new geometric relation between a solid bounded by a smooth surface and its silhouette in images formed under weak perspective projection. The relation has the potential to be used for recognizing complex 3-D objects from a single image. Objects are modeled by showing them to a camera without any knowledge of their motion. The main idea is to consider the dual of the 3-D surface and the family of dual curves of the silhouettes over all viewing directions. Occluding contours correspond to planar slices of the dual surface. We introduce an affine-invariant representation of this surface that can constructed from a sequence of images and allows an object to be recognized from arbitrary viewing directions. We illustrate the proposed object representation scheme through synthetic examples and image contours detected in real images.

Keywords

Tangent Line Image View Initial Curve Rigid Transformation Image Contour 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. [1]
    E. Arbogast and R. Mohr. 3D structure inference from image sequences. Journal of Pattern Recognition and Artificial Intelligence, 5(5), 1991.Google Scholar
  2. [2]
    E. Boyer and M. Berger. 3d surface reconstruction using occluding contours. Int. J. Computer Vision, 22(3):219–233, 1997.CrossRefGoogle Scholar
  3. [3]
    J. Bruce and P. Giblin. Curves and Singularities. Cambridge University Press, 1992.Google Scholar
  4. [4]
    R. Cipolla, K. Aström, and P. Giblin. Motion from the frontier of curved surfaces. In Int. Conf. on Computer Vision, pages 269–275, 1995.Google Scholar
  5. [5]
    R. Cipolla and A. Blake. Surface shape from the deformation of the apparent contour. Int. J. Computer Vision, 9(2):83–112, November 1992.Google Scholar
  6. [6]
    M. do Carmo. Differential Geometry of Curves and Surfaces. Prentice-Hall, Englewood Cliffs, N.J., 1976.zbMATHGoogle Scholar
  7. [7]
    P. Giblin and R. Weiss. Epipolar curves on surfaces. Image and Vision Computing, 13(1):33–44, 1995.CrossRefGoogle Scholar
  8. [8]
    R. Glachet, M. Dhome, and J. Lapersté. Finding the perspective projection of an axis of revolution. Pattern Recognition Letters, 12:693–700, 1991.CrossRefGoogle Scholar
  9. [9]
    D. Huttenlocher and S. Ullman. Recognizing solid objects by alignment with an image. IJCV, 5(2):195–212, November 1990.Google Scholar
  10. [10]
    T. Joshi, B. Vijayakumar, D. Kriegman, and J. Ponce. HOT curves for modelling and recognition of smooth curved 3D shapes. Image and Vision Computing, pages 479–498, July 1997.Google Scholar
  11. [11]
    J. J. Koenderink. What does the occluding contour tell us about solid shape? Perception, 13, 1984.Google Scholar
  12. [12]
    D. Kriegman and J. Ponce. On recognizing and positioning curved 3D objects from image contours. IEEE Trans. Pattern Anal. Mach. Intelligence, 12(12):1127–1137, 1990.CrossRefGoogle Scholar
  13. [13]
    D. J. Kriegman and J. Ponce. Computing exact aspect graphs of curved objects: Solids of revolution. Int. J. Computer Vision, 5(2):119–135, 1990.CrossRefGoogle Scholar
  14. [14]
    J. Liu, J. Mundy, D. Forsyth, A. Zisserman, and C. Rothwell. Efficient recognition of rotationally symmetric surfaces and straight homogeneous generalized cylinders. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 123–128, 1993.Google Scholar
  15. [15]
    D. G. Lowe. The viewpoint consistency constraint. Int. J. Computer Vision, 1(1):57–72, 1987.CrossRefGoogle Scholar
  16. [16]
    A. Mackworth and F. Mokhtarian. The renormalized curvature scale space and the evolution properties of planar curves. In Proc. IEEE Conf. on Comp. Vision and Patt. Recog., pages 318–326, 1988.Google Scholar
  17. [17]
    H. Murase and S. Nayar. Visual learning and recognition of 3-D objects from appearence. Int. J. Computer Vision, 14(1):5–24, 1995.CrossRefGoogle Scholar
  18. [18]
    S. Petitjean, J. Ponce, and D. Kriegman. Computing exact aspect graphs of curved objects: Algebraic surfaces. Int. J. Computer Vision, 9(3):231–255, 1992.CrossRefGoogle Scholar
  19. [19]
    J. Ponce and D. Chelberg. Finding the limbs and cusps of generalized cylinders. Int. J. Computer Vision, 1(3), October 1987.Google Scholar
  20. [20]
    J. Ponce, A. Hoogs, and D. Kriegman. On using CAD models to compute the pose of curved 3D objects. CVGIP: Image Understanding, 55(2):184–197, Mar. 1992.Google Scholar
  21. [21]
    M. Richetin, M. Dhome, J. Lapresté, and G. Rives. Inverse perspective transform from zero-curvature curve points: Application to the localization of some generalized cylinders from a single view. IEEE Trans. Pattern Anal. Mach. Intelligence, 13(2):185–191, February 1991.Google Scholar
  22. [22]
    J. Rieger. Global bifurcations sets and stable projections of non-singular algebraic surfaces. Int. J. Computer Vision, 7(3):171–194, 1992.CrossRefGoogle Scholar
  23. [23]
    R. Vaillant and O. Faugeras. Using extremal boundaries for 3D object modeling. IEEE Trans. Pattern Anal. Mach. Intelligence, 14(2):157–173, February 1992.Google Scholar
  24. [24]
    B. Vijayakumar, D. Kriegman, and J. Ponce. Invariant-based recognition of complex curved 3-D objects from image contours. Computer Vision and Image Understanding, pages 287–303, Dec. 1998.Google Scholar
  25. [25]
    M. Zeroug and G. Medioni. The challenge of generic object recognition. In M. Hebert, J. Ponce, T. Boult, and A. Gross, editors, Object Representation for Computer Vision, pages 271–232. Springer-Verlag, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • David Renaudie
    • 1
  • David Kriegman
    • 2
  • Jean Ponce
    • 2
  1. 1.Ecole Nationale Supérieure dÍnformatique et MathématiquesAppliquées de GrenobleSt Martin d’HèeresFrance
  2. 2.Department of Computer ScienceUniversity Of IllinoisUrbanaUSA

Personalised recommendations