Advertisement

Intrinsic Images for Dense Stereo Matching with Occlusions

  • César Silva
  • José Santos-Victor
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1842)

Abstract

Stereo correspondence is a central issue in computer vision. The traditional approach involves extracting image features, establishing correspondences based on photometric and geometric criteria and finally, determine a dense disparity field by interpolation. In this context, occlusions are considered as undesirable artifacts and often ignored.

The challenging problems addressed in this paper are a) finding an image representation that facilitates (or even trivializes) the matching procedure and, b) detecting and including occlusion points in such representation.

We propose a new image representation called Intrinsic Images that can be used to solve correspondence problems within a natural and intuitive framework. Intrinsic images combine photometric and geometric descriptors of a stereo image pair. We extend this framework to deal with occlusions and brightness changes between two views.

We show that this new representation greatly simplifies the computation of dense disparity maps and the synthesis of novel views of a given scene, obtained directly from this image representation. Results are shown to illustrate the performance of the proposed methodology, under perspective effects and in the presence of occlusions.

References

  1. 1.
    B. L. Anderson and K. Nakayama. Toward a general theory of stereopsis: Binocular matching, occluding contours, and fusion. Psych. Review, 101:414–445, 1994.CrossRefGoogle Scholar
  2. 2.
    T. Cormen, C. Leiserson, and R. Rivest. Introduction to Algorithms. The MIT Press, 1990.Google Scholar
  3. 3.
    U. R. Dhond and J. K. Aggarwal. Stereo matching in the presence of narrow occluding objects using dynamics disparity search. PAMI, 17(7):719–724, July 1995.Google Scholar
  4. 4.
    R. Haralick and L. Shapiro. Computer and Robot Vision, volume 2. Addison-Wesley, 1993.Google Scholar
  5. 5.
    Y. Ohta and T. Kanade. Stereo by intra-and inter-scanline search using dynamic programming. PAMI, 7(2):139–154, 1985.Google Scholar
  6. 6.
    C. Silva and J. Santos-Victor. Robust egomotion estimation from the normal flow using search subspaces. PAMI, 19(9):1026–1034, September 1997.Google Scholar
  7. 7.
    C. Silva and J. Santos-Victor. Motion from occlusions. In Proc. of 7th International Symposium on Intelligent Robotic Systems, 1999.Google Scholar
  8. 8.
    C. Tomasi and R. Manduchi. Stereo without search. In Proc. of European Conference on Computer Vision. Springer-Verlag, 1996.Google Scholar
  9. 9.
    J. Weng, N. Ahuja, and T. Huang. Matching two perspective views. PAMI, 14(8):806–825, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • César Silva
    • 1
  • José Santos-Victor
    • 1
  1. 1.Instituto de Sistemas e Robótica Instituto Superior TécnicoLisboaPortugal

Personalised recommendations