Advertisement

Probabilistic Signal Models to Regularise Dynamic Programming Stereo

  • Georgy Gimel’farb
  • Uri Lipowezky
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)

Abstract

Ill-posedness of the binocular stereo problem stems from partial occlusions and homogeneous textures of a 3D surface. We consider the symmetric dynamic programming stereo regularised with respect to partial occlusions. The regularisation is based on Markovian models of epipolar profiles and stereo signals that allow for measuring similarity of stereo images with due account of binocular and monocular visibility of the surface points. Experiments show that the probabilistic regularisation yields mostly accurate elevation maps but fails in excessively occluded or shaded areas.

References

  1. 1.
    Bensrhair, A., Miché, P., Debrie, R.:Fast and automatic stereo vision matching algorithm based on dynamic programming method. Pattern Recognition Letters 17 (1996) 457–466CrossRefGoogle Scholar
  2. 2.
    Cox, I. J., Hingorani, S. L., Rao, S. B.: A maximum likelihood stereo algorithm. Computer Vision and Image Understanding 63 (1996) 542–567CrossRefGoogle Scholar
  3. 3.
    Gimel’farb, G. L.: Intensity-based computer binocular stereo vision: signal models and algorithms. Int. Journal of Imaging Systems and Technology 3 (1991) 189–200CrossRefGoogle Scholar
  4. 4.
    Gimel’farb, G.: Stereo terrain reconstruction by dynamic programming. In: Jaehne, B., Haussecker, H., Geisser, P. (Eds.): Handbook of Computer Vision and Applications. Academic Press, San Diego, vol. 2 (1999) 505–530Google Scholar
  5. 5.
    Gimel’farb, G.: Binocular stereo by maximizing the likelihood ratio relative to a random terrain. In: Klette, R., Peleg, S., Sommer, G. (Eds.): Robot Vision (Lecture Notes in Computer Science 1998). Springer, Berlin (2001) 201–208Google Scholar
  6. 6.
    Li, Z.-N.: Stereo correspondence based on line matching in Hough space using dynamic programming. IEEE Trans. on Systems, Man, and Cybernetics 24 (1994) 144–152CrossRefGoogle Scholar
  7. 7.
    Rojas, A., Calvo, A., Munõz, J.: A dense disparity map of stereo images. Pattern Recognition Letters 18 (1997) 385–393CrossRefGoogle Scholar
  8. 8.
    Vergauwen, M., Pollefeys, M., Van Gool, L.: A stereo vision system for support of planetary surface exploration. In: Schiele, B, Sagerer, G. (Eds.): Computer Vision Systems Second Int. Workshop (ICVS 2001), Vancouver, Canada, July 7–8, 2001 (Lecture Notes in Computer Science 2095). Springer, Berlin (2001) 298–312Google Scholar
  9. 9.
    Yip, R. K. K., Ho, W. P.: A multi-level dynamic programming method for stereo line matching. Pattern Recognition Letters 19 (1998) 839–855CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Georgy Gimel’farb
    • 1
  • Uri Lipowezky
    • 2
  1. 1.CITR, Department of Computer Science, Tamaki CampusUniversity of AucklandAuckland 1New Zealand
  2. 2.Tiltan System Engineering Ltd.Beney - BeraqIsrael

Personalised recommendations