Adaptive stereo matching in correlation scale-space

  • Christian Menard
  • Walter G. Kropatsch
Session 7: Motion & Stereo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


Stereo computes the distance of objects, “their depth”, from two images of two cameras using the triangulation principle. Points of imaged objects are mapped in different locations in the two stereo images. A central problem in stereo matching using correlation techniques lies in selecting the size of the search window. Small windows contain only a small number of data points, and thus are very sensitive to noise and therefore result in false matches. Whereas large search windows contain data from two or more different objects or surfaces, thus the estimated disparity is not accurate due to different projective distortions in the left and the right image. The new method introduces a continuous scale parameter for the matching process. It allows the adaption of the scale for every individual region and overcomes the drawbacks of fixed window sizes which is impressively demonstrated by the experimental results.


Stereo Image Search Window Optimal Scale Stereo Match Stereo Pair 
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.


  1. 1.
    S.T. Barnard and M.A. Fischler. Computational stereo. In ACM Computing Surveys, volume 14, pages 553–572, Dec. 1982.Google Scholar
  2. 2.
    M. Jaegersand. Saliency maps and attention selection in scale and spatial coordinates: An information theoretic approach. In Proceedings Fifth Intern. Conf. on Computer Vision, pages 195–202, Cambridge, MA, June 20–23 1995. MIT, IEEE. Catalogue no 95CB35744.Google Scholar
  3. 3.
    T. Kanade and M. Okutomi. A stereo matching algorithm with an adaptive window: Theory and experiment. PAMI, 16(9):920–932, September 1994.Google Scholar
  4. 4.
    M.D. Levine, D.A. O'Handley, and G.M. Yagi. Computer determination of depth maps. Comput. Graphics Image Processing, 2:131–150, September 1973.Google Scholar
  5. 5.
    L. Lindeberg. Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, 1994.Google Scholar
  6. 6.
    C. Menard. Robust Stereo and Adaptive Matching in Correlation Scale-Space. PhD thesis, TU Wien, Institut für Automation, PRIP, Wien, 1996.Google Scholar
  7. 7.
    C. Menard and R. Sablatnig. Computer based Acquisition of Archaeological Finds: The First Step towards Automatic Classification. In Hans Kamermans and Kelly Fennema, editors, Interfacing the Past. Computer Applications and Quantitative Methods in Archaeology. CAA95, number 28, pages 413–424, Leiden, March 1996. Analecta Praehistorica Leidensia.Google Scholar
  8. 8.
    Azriel Rosenfeld and Avinash C. Kak. Digital Picture Processing Volume 2. Academic Press, Inc., 1982.Google Scholar
  9. 9.
    R. Sablatnig and C. Menard. Stereo and Structured Light as Acquisition Methods in the Field of Archaeology. In New York Springer Verlag Berlin, Heidelberg, editor, Mustererkennung 92 14. DAGM Symposium Dresden, pages 398–404. Fuchs S., 1992.Google Scholar
  10. 10.
    J. Weng. Camera calibration with distortion models and accuracy evaluation. IEEE Trans. Patt. Anal. Machine Intell., 14:965–980, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Christian Menard
    • 1
  • Walter G. Kropatsch
    • 1
  1. 1.Pattern Recognition and Image Processing GroupVienna University of TechnologyViennaAustria

Personalised recommendations