Robust Computer Vision through Kernel Density Estimation

  • Haifeng Chen
  • Peter Meer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2350)


Two new techniques based on nonparametric estimation of probability densities are introduced which improve on the performance of equivalent robust methods currently employed in computer vision. The first technique draws from the projection pursuit paradigm in statistics, and carries out regression M-estimation with a weak dependence on the accuracy of the scale estimate. The second technique exploits the properties of the multivariate adaptive mean shift, and accomplishes the fusion of uncertain measurements arising from an unknown number of sources. As an example, the two techniques are extensively used in an algorithm for the recovery of multiple structures from heavily corrupted data.


Kernel Density Estimation Vision Task Robust Regression Scale Estimate Kernel Density Estimator 
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.
    L. Breiman. Bagging predictors. Machine Learning, 24:123–140, 1996.zbMATHMathSciNetGoogle Scholar
  2. 2.
    H. Chen, P. Meer, and D. E. Tyler. Robust regression for data with multiple structures. In 2001 IEEE Conference on Computer Vision and Pattern Recognition, volume I, pages 1069–1075, Kauai, HI, December 2001.Google Scholar
  3. 3.
    D. Comaniciu and P. Meer. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell., 24, May 2002.Google Scholar
  4. 4.
    D. Comaniciu, V. Ramesh, and P. Meer. The variable bandwidth mean shift and data-driven scale selection. In 8th International Conference on Computer Vision, volume I, pages 438–445, Vancouver, Canada, July 2001.Google Scholar
  5. 5.
    J. Costeira and T. Kanade. A multiple factorization method for motion analysis. International J. of Computer Vision, 29:159–179, 1998.CrossRefGoogle Scholar
  6. 6.
    D. Donoho, I. Johnstone, P. Rousseeuw, and W. Stahel. Discussion: Projection pursuit. Annals of Statistics, 13:496–500, 1985.CrossRefGoogle Scholar
  7. 7.
    R. O. Duda, P. E. Hart, and D. G. Stork. Pattern Classification. Wiley, second edition, 2000.Google Scholar
  8. 8.
    K. Fukunaga and L. D. Hostetler. The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Information Theory, 21:32–40, 1975.zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    P. J. Huber. Projection pursuit (with discussion). Annals of Statistics, 13:435–525, 1985.zbMATHMathSciNetCrossRefGoogle Scholar
  10. 10.
    M. Irani and P. Anandan. Video indexing based on mosaic representations. Proceedings of IEEE, 86:905–921, 1998.CrossRefGoogle Scholar
  11. 11.
    M. C. Jones and R. Sibson. What is projection pursuit? (with discussion). J. of the Royal Stat. Soc. Series A, 150:1–37, 1987.zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    K. Kanatani. Motion segmentation by subspace separation and model selection. In 8th International Conference on Computer Vision, volume II, pages 301–306, Vancouver, Canada, July 2001.Google Scholar
  13. 13.
    G. Li. Robust regression. In D. C. Hoaglin, F. Mosteller, and J. W. Tukey, editors, Exploring Data Tables, Trends, and Shapes, pages 281–343. John Wiley & Sons, 1985.Google Scholar
  14. 14.
    P. J. Rousseeuw and A. M. Leroy. Robust Regression and Outlier Detection. Wiley, 1987.Google Scholar
  15. 15.
    H. S. Sawhney, Y. Guo, and R. Kumar. Independent motion detection in 3D scenes. IEEE Trans. Pattern Anal. Machine Intell., 22:1191–1199, 2000.CrossRefGoogle Scholar
  16. 16.
    B. W. Silverman. Density Estimation for Statistics and Data Analysis. Chapman & Hall, 1986.Google Scholar
  17. 17.
    Special Issue. Robust statistical techniques in image understanding. Computer Vision and Image Understanding, 78, April 2000.Google Scholar
  18. 18.
    D. M. J. Tax, M. van Breukelen, R. P. W. Duin, and J. Kittler. Combining multiple classifiers by averaging or by multiplying? Pattern Recog., 33:1475–1486, 2000.CrossRefGoogle Scholar
  19. 19.
    M. P. Wand and M. C. Jones. Kernel Smoothing. Chapman & Hall, 1995.Google Scholar
  20. 20.
    R. H. Zamar. Robust estimation in the errors-in-variables model. Biometrika, 76:149–160, 1989.zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Haifeng Chen
    • 1
  • Peter Meer
    • 1
  1. 1.Electrical and Computer Engineering DepartmentRutgers UniversityPiscatawayUSA

Personalised recommendations