Using Colour for Robust Tracking and Segmentation

  • Yogesh Raja
  • Stephen McKenna
  • Shaogang Gong
Conference paper


We use colour mixture models for real-time colour-based object localisation, tracking and segmentation in dynamic scenes, motivated by applications such as virtual studios and recognition of human faces, gestures and actions. We address the issues of model order selection, modelling scene background and model adaptation in time. Experimental results are given to demonstrate our approach under varying viewing and lighting conditions.


Mixture Model Colour Model Colour Distribution Dynamic Scene Multiple Object Tracking 
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]
    Y. Raja, S. McKenna, and S. Gong, “Segmentation and tracking using colour mixture models,” in ACCV, Hong Kong, January 1998.Google Scholar
  2. [2]
    S. McKenna, S. Gong, and Y. Raja, “Face recognition in dynamic scenes,” in BMVC, 1997.Google Scholar
  3. [3]
    M. J. Swain and D. H. Ballard, “Colour indexing,” IJCV, pp. 11–32, 1991.Google Scholar
  4. [4]
    S. McKenna, S. Gong, and Y. Raja, “Tracking colour objects using adaptive mixture models,” Image and Vision Computing, 1998, In Press.Google Scholar

Copyright information

© Springer-Verlag London Limited 1998

Authors and Affiliations

  • Yogesh Raja
    • 1
  • Stephen McKenna
    • 2
  • Shaogang Gong
    • 3
  1. 1.Dept. of Computer ScienceQueen Mary and Westfield CollegeLondon, England
  2. 2.Dept. of Applied ComputingUniversity of DundeeScotland
  3. 3.Dept. of Computer ScienceQMWEngland

Personalised recommendations