Robust location based partial correlation

  • Zhong-Dan Lan
  • Roger Mohr
Stereo and Correspondence
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1296)


The visual correspondence problem is a major issue in computer vision. Correlation is a common tool for this problem. Most classical correlation methods fail near the disparity discontinuities, which occur at the boundaries of objects. In this paper, a partial correlation technique is proposed to solve this problem. Robust location methods are used to perform this partial correlation. Comparisons are made with other techniques and experimental results validate the approach.


Partial Correlation Partial Occlusion Stereo Match Robust Regression Pixel Error 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    P. Aschwanden and W. Guggenbiihl. Experimental results from a comparative study on correlation-type registration algorithms. In Förstner and Ruwiedel, editors, Robust Computer Vision, pages 268–282. Wichmann, 1992.Google Scholar
  2. 2.
    D.H. Ballard and C.M. Brown. Computer Vision. Prentice Hall, 1982.Google Scholar
  3. 3.
    P. Fua. A parallel stereo algorithm that produces dense depth maps and preserves image features. Machine Vision and Applications, 1990.Google Scholar
  4. 4.
    D. Geiger, B. Ladendorf, and A. Yuille. Occlusions and binocular stereo. In G. Sandini, editor, Proceedings of the 2nd European Conference on Computer Vision, Santa Margherita Ligure, Italy, pages 425–433. Springer Verlag, 1992.Google Scholar
  5. 5.
    B.K.P. Horn. Robot Vision. The MIT Press, 1986.Google Scholar
  6. 6.
    S.S. Intille and A.F. Bobick. Disparity-space images and large occlusion stereo. In Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden, pages 179–186. Springer-Verlag, 1994.Google Scholar
  7. 7.
    J.M. Jolion, P. Meer, and S. Bataouche. Robust clustering with applications in computer vision. PAMI, 13(8):791–802, August 1991.Google Scholar
  8. 8.
    Z. D. Lan, R. Mohr, and P. Remagnino. Robust matching by partial correlation. In Proceedings of the sixth British Machine Vision Conference, Birmingham, England, pages 651–660, September 1995.Google Scholar
  9. 9.
    Z.D. Lan and R. Mohr. Robust location based partial correlation. Technical report, Institut National Polytechnique de Grenoble, Movi, Gravir, Inria, 655 avenue de l'Europe 38330 Montbonnot, 1997. to appear.Google Scholar
  10. 10.
    D. Marr. Vision. W.H. Freeman and Company, San Francisco, California, USA, 1982.Google Scholar
  11. 11.
    H.K. Nishihara. PRISM, a pratical real-time imaging stereo matcher. Technical Report Technical Report A.I. Memo 780, Massachusetts Institute of Technology, 1984.Google Scholar
  12. 12.
    P.J. Rousseeusw and A.M. Leroy. Robust regression and outlier detection, volume XIV of Wiley. J.Wiley and Sons, New York, 1987.Google Scholar
  13. 13.
    P. Seitz. Using local orientational information as image primitive for robust object recognition. In SPIE proceedings, pages 1630–1639, 1989.Google Scholar
  14. 14.
    R. Zabih and J. Woodfill. Non-parametric local transforms for computing visual correspondance. In Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden, pages 151–158. Springer-Verlag, May 1994.Google Scholar
  15. 15.
    J. Zhao. Extraction d'information tri-dimensionnelle par stéréovision. Thèse de doctorat, Université Paul Sabatier, Toulouse, July 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Zhong-Dan Lan
    • 1
  • Roger Mohr
    • 1
  1. 1.Projet MoviLaboratoire GravirMontbonnotFrance

Personalised recommendations