Accelerated Convergence Using Dynamic Mean Shift

  • Kai Zhang
  • Jamesk T. Kwok
  • Ming Tang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


Mean shift is an iterative mode-seeking algorithm widely used in pattern recognition and computer vision. However, its convergence is sometimes too slow to be practical. In this paper, we improve the convergence speed of mean shift by dynamically updating the sample set during the iterations, and the resultant procedure is called dynamic mean shift (DMS). When the data is locally Gaussian, it can be shown that both the standard and dynamic mean shift algorithms converge to the same optimal solution. However, while standard mean shift only has linear convergence, the dynamic mean shift algorithm has superlinear convergence. Experiments on color image segmentation show that dynamic mean shift produces comparable results as the standard mean shift algorithm, but can significantly reduce the number of iterations for convergence and takes much less time.


Step Length Segmentation Result Superlinear Convergence Shift Vector Linear Convergence 
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.
    Fukunaga, K., Hostetler, L.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transactions on Information Theory 21, 32–40 (1975)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Cheng, Y.: Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 790–799 (1995)CrossRefGoogle Scholar
  3. 3.
    Comaniciu, D.: An algorithm for data-driven bandwidth selection. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 281–288 (2003)CrossRefGoogle Scholar
  4. 4.
    Georgescu, B., Shimshoni, I., Meer, P.: Mean shift based clustering in high dimensions: A texture classification example. In: Proceedings of the International Conference on Computer Vision, pp. 456–463 (2003)Google Scholar
  5. 5.
    Comaniciu, D., Meer, P.: The variable bandwidth mean shift and data driven scale selection. In: Proc. ICCV, pp. 438–445 (2001)Google Scholar
  6. 6.
    Comaniciu, D., Meer, P.: Mean shift: A robust approach towards feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 603–619 (2002)CrossRefGoogle Scholar
  7. 7.
    Zivkovic, Z., Kröse, B.: An EM-like algorithm for color-histogram-based object tracking. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 798–803 (2004)Google Scholar
  8. 8.
    DeMenthon, D., Doermann, D.: Video retrieval using spatio-temporal descriptors pages. In: Proceedings of the Eleventh ACM International Conference on Multimedia, pp. 508–517 (2003)Google Scholar
  9. 9.
    Yang, C., Duraiswami, R., DeMenthon, D., Davis, L.: Mean-shift analysis using quasi-Newton methods. In: Proceedings of the International Conference on Image Processing, vol. 3, pp. 447–450 (2003)Google Scholar
  10. 10.
    Fashing, M., Tomasi, C.: Mean shift is a bound optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 471–474 (2005)CrossRefGoogle Scholar
  11. 11.
    Stoker, T.: Smoothing bias in density derivative estimation. Journal of the American Statistical Association 88, 855–863 (1993)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Comaniciu, D., Meer, P.: Distribution free decomposition of multivariate data. Pattern Analysis and Applications 2, 22–30 (1999)CrossRefzbMATHGoogle Scholar
  13. 13.
    Zhang, K., Tang, M., Kwok, J.T.: Applying neighborhood consistency for fast clustering and kernel density estimation. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, pp. 1001–1007 (2005)Google Scholar
  14. 14.
    Fletcher, R.: Practical Methods of Optimization. Wiley, New York (1987)zbMATHGoogle Scholar
  15. 15.
    Noble, B., Daniel, J.: Applied Linear Algebra, 3rd edn. Prentice-Hall, Englewood Cliffs (1988)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Kai Zhang
    • 1
  • Jamesk T. Kwok
    • 1
  • Ming Tang
    • 2
  1. 1.Department of Computer ScienceThe Hong Kong University of Science and TechnologyKowloon, Hong KongHong Kong
  2. 2.National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijingChina

Personalised recommendations