Advertisement

Binocular Stereo by Maximizing the Likelihood Ratio Relative to a Random Terrain

  • Georgy Gimel’farb
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1998)

Abstract

A novel approach to computational binocular stereo based on the Neyman-Pearson criterion for discriminating between statistical hypotheses is proposed. An epipolar terrain profile is reconstructed by maximizing its likelihood ratio with respect to a purely random profile. A simple generative Markov-chain model of an image-driven profile that extends the model of a random profile is introduced. The extended model relates transition probabilities for binocularly and monocularly visible points along the profile to grey level differences between corresponding pixels in mutually adapted stereo images. This allows for regularizing the ill-posed stereo problem with respect to partial occlusions.

Keywords

Stereo Image Partial Occlusion Stereo Match Stereo Pair Stationary Markov Chain 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    H. H. Baker: Surfaces from mono and stereo images. Photogrammetria 39 (1984) 217–237. 201CrossRefGoogle Scholar
  2. 2.
    W. Förstner: Image matching. In: R. M. Haralick and L. G. Shapiro: Computer and Robot Vision. Vol. 2, chapter 16. Reading, Addison-Wesley (1993) 289–378.201Google Scholar
  3. 3.
    G. L. Gimel’farb: Intensity-based computer binocular stereo vision: signal models and algorithms. Int. J. of Imaging Systems and Technology 3 (1991) 189–200. 201, 202, 203, 204CrossRefGoogle Scholar
  4. 4.
    G. L. Gimel’farb: Regularization of low-level binocular stereo vision considering surface smoothness and dissimilarity of superimposed stereo images. In: C. Arcelli, L. P. Cordella, G. Sanniti di Baja (eds.): Aspects of Visual Form Processing. Singapore, World Scientific (1994) 231–240. 202, 203Google Scholar
  5. 5.
    G. L. Gimel’farb: Symmetric bi-and trinocular stereo: tradeoffs between theoretical foundations and heuristics. Computing Supplement 11 (1996) 53–72. 202, 203Google Scholar
  6. 6.
    G. Gimel’farb: Stereo terrain reconstruction by dynamic programming. In: B. Jaehne, H. Haussecker, P. Geisser (eds.): Handbook of Computer Vision and Applications 2: Signal Processing and Pattern Recognition. San Diego, Academic Press (1999) 505–530. 201, 202, 203, 204Google Scholar
  7. 7.
    G. Gimel’farb, H. Li: Probabilistic regularization in symmetric dynamic programming stereo. In: Proc. of the Image and Vision Computing New Zealand’2000 Conf., November 2000, Hamilton, New Zealand. (2000) [to appear]. 202, 205, 208Google Scholar
  8. 8.
    M. J. Hannah: Digital stereo image matching techniques. Int. Archives on Photogrammetry and Remote Sensing 27 (1988) 280–293. 201Google Scholar
  9. 9.
    T. Kanade, M. Okutomi: A stereo matching algorithm with an adaptive window: theory and experiment. IEEE Trans. on Pattern Analysis and Machine Intelligence 16 (1994) 920–932. 201CrossRefGoogle Scholar
  10. 10.
    M. G. Kendall, A. Stuart: The Advanced Theory of Statistics. 2: Inference and Relationship. London, Charles Griffin (1967). 202Google Scholar
  11. 11.
    V. R. Kyreitov: Inverse Problems of Photometry. Novosibirsk, Computing Center of the Siberian Branch of the Academy of Sciences of the USSR (1983) [In Russian]. 201Google Scholar
  12. 12.
    T. Poggio, V. Torre, C. Koch: Computational vision and regularization theory. Nature 317 (1985) 317–319. 201CrossRefGoogle Scholar
  13. 13.
    G.-Q. Wei, W. Brauer,, G. Hirzinger: Intensity-and gradient-based stereo matching using hierarchical Gaussian basis functions. IEEE Trans. on Pattern Analysis and Machine Intelligence 20 (1998) 1143–1160. 201CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Georgy Gimel’farb
    • 1
  1. 1.CITR, Department of Computer Science, Tamaki CampusUniversity of AucklandAucklandNew Zealand

Personalised recommendations