Skip to main content

Dense Two-Frame Stereo Correspondence by Self-organizing Neural Network

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNIP,volume 5716)

Abstract

This work aims at defining an extension of a competitive method for matching correspondences in stereoscopic image analysis. The method we extended was proposed by Venkatesh, Y.V. et al where the authors extend a Self-Organizing Map by changing the neural weights updating phase in order to solve the correspondence problem within a two-frame area matching approach and producing dense disparity maps. In the present paper we have extended the method mentioned by adding some details that lead to better results. Experimental studies were conducted to evaluate and compare the solution proposed.

Keywords

  • Stereo matching
  • self-organizing map
  • disparity map
  • occlusions

References

  1. Ballard, D.H., Brown, C.M.: Computer Vision. Prentice-Hall, Englewood Cliffs (1982)

    Google Scholar 

  2. Faugeras, O.: Three-dimensional computer vision: a geometric viewpoint. MIT Press, Cambridge (1993)

    Google Scholar 

  3. Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47, 7–42 (2002)

    CrossRef  MATH  Google Scholar 

  4. Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)

    MATH  Google Scholar 

  5. Binaghi, E., Gallo, I., Marino, G., Raspanti, M.: Neural adaptive stereo matching. Pattern Recognition Letters 25, 1743–1758 (2004)

    CrossRef  Google Scholar 

  6. Gallo, I., Binaghi, E., Raspanti, M.: Neural disparity computation for dense two-frame stereo correspondence. Pattern Recogn. Lett. 29(5), 673–687 (2008)

    CrossRef  Google Scholar 

  7. Venkatesh, Y.V., Raja, S.K., Kumar, A.J.: On the application of a modified self-organizing neural network to estimate stereo disparity. IEEE Transactions on Image Processing 16(11), 2822–2829 (2007)

    MathSciNet  CrossRef  Google Scholar 

  8. Kohonen, T.: Self-organizing formation of topologically correct feature maps. Biological Cybernetics 43(1), 59–69 (1982)

    MathSciNet  CrossRef  MATH  Google Scholar 

  9. Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: Proceedings. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. I–195–I–202 (2003)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Vanetti, M., Gallo, I., Binaghi, E. (2009). Dense Two-Frame Stereo Correspondence by Self-organizing Neural Network. In: Foggia, P., Sansone, C., Vento, M. (eds) Image Analysis and Processing – ICIAP 2009. ICIAP 2009. Lecture Notes in Computer Science, vol 5716. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04146-4_110

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-04146-4_110

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-04145-7

  • Online ISBN: 978-3-642-04146-4

  • eBook Packages: Computer ScienceComputer Science (R0)