Skip to main content

Fast algorithm for the stereo pair matching with parallel computation

  • 3-D Vision
  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 719))

Abstract

An algorithm for the stereo pair matching is considered. This algorithm relies on the local correlation analysis at an image pyramid. The parallaxes are defined iteratively over the pyramid layers from top (with poor spatial resolution) to bottom (with finest spatial resolution). The matching algorithm consist of three stages: (1) pyramid construction, (2) feature system developing on the each pyramid layer, (3) correspondence points searching. Dynamic programming method is used to match the points along the horisontal scanline for the stereo pair without y-parallaxes. Parallel computation on the transputer system is used to accelerate the matching process.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. S.B.Marapane, M.M.Trivedy: Region-based stereo analysis for robotic application. IEEE Trans. on Systems, Man and Cybernetics, Vol.19, No.6, November/December 1989.

    Google Scholar 

  2. R. Nevatia: Machine Perception. Englewood Cliffs, NJ:Practice Hall, 1982.

    Google Scholar 

  3. M.J.Hannah: A system for digital stereo image matching. Photogrammetric Engineering and Remote Sensing, Vol.55, No.12, December 1989, pp.1765–1770.

    Google Scholar 

  4. H.J.Lee, W.L. Lei: Region matching and depth finding for 3D objects in stereo aerial photographs. Pattern Recognition, Vol.23, No.1/2, 1990, pp.81–94.

    Google Scholar 

  5. G.L.Gimelfarb: Automatic measurement of space coordinates on a landscape from the stereo pair. The Questions of Robotics and Artificial intelligence. Institute of Cybernetics, USSR, 1977, pp. 3–13.

    Google Scholar 

  6. Y.Ohta, T.Kanade: Stereo by Intra-and-Inter Scanline Search Using Dynamic Programming. IEEE Trans. on Pattern. Anal. Machine Intell. Vol.PAMI-7, No.2, March, 1985.

    Google Scholar 

  7. Y.C. Kim, J.K. Aggarwal: Positioning 3-D objects using stereo images. IEEE J. Robotics and Automation, Vol.RA-3, No.4. Aug. 1987. pp.361–373.

    Google Scholar 

  8. S.T. Barnard:A stochastic approach to stereo vision. Tech. Rep.373, SRI International, Menlo Park, CA 94025, Apr. 1986.

    Google Scholar 

  9. D.A. Usikov, M.I. Kolesnik: Algorithm for stereo pair matching. Cospar Colloquia, Vol.2, Jan., 1990, pp.47–50.

    Google Scholar 

  10. M.I.Kolesnik: The automatic reconstruction of 3-dimensional scene for Mars rover operations. Proc.ESA Symp.:“Ground data systems for spacecraft control”, Darmstadt, FRG, 26–29 June, 1990, pp.247–250.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Dmitry Chetverikov Walter G. Kropatsch

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kolesnik, M.I. (1993). Fast algorithm for the stereo pair matching with parallel computation. In: Chetverikov, D., Kropatsch, W.G. (eds) Computer Analysis of Images and Patterns. CAIP 1993. Lecture Notes in Computer Science, vol 719. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57233-3_70

Download citation

  • DOI: https://doi.org/10.1007/3-540-57233-3_70

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-57233-6

  • Online ISBN: 978-3-540-47980-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics