Traffic Video Segmentation Using Adaptive-K Gaussian Mixture Model

  • Rui Tan
  • Hong Huo
  • Jin Qian
  • Tao Fang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4153)


Video segmentation is an important phase in video based traffic surveillance applications. The basic task of traffic video segmentation is to classify pixels in the current frame to road background or moving vehicles, and casting shadows should be taken into account if exists. In this paper, a modified online EM procedure is proposed to construct Adaptive-K Gaussian Mixture Model (AKGMM) in which the dimension of the parameter space at each pixel can adaptively reflects the complexity of pattern at the pixel. A heuristic background components selection rule is developed to make pixel classification decision based on the proposed model. Our approach is demonstrated to be more adaptive, accurate and robust than some existing similar pixel modeling approaches through experimental results.


Gaussian Mixture Model Background Image Gaussian Component Background Component Stationary Vehicle 
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.
    Piccardi, M.: Background Subtraction Techniques: A Review. In: 2004 IEEE International Conference on Systems, Man and Cybernetics, pp. 3099–3104 (2004)Google Scholar
  2. 2.
    Michalopoulos, P.G.: Vehicle Detection Video Through Image Processing: The Autosope System. IEEE Trans. on Vehicular Technology 40(1) (February 1991)Google Scholar
  3. 3.
    Friedman, N., Russell, S.: Image Segmentation in Video Sequences: A Probabilistic Approach. In: Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence(UAI), San Francisco (1997)Google Scholar
  4. 4.
    Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.P.: Pfinder: Real-time Tracking of the Human Body. IEEE Trans. on Pattern Analysis and Machine Intelligence 19(7) (July 1997)Google Scholar
  5. 5.
    Stauffer, C., Grimson, W.E.L.: Adaptive Background Mixture Models for Read-Time Tracking. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252 (1999)Google Scholar
  6. 6.
    Stauffer, C., Grimson, W.E.L.: Learning Patterns of Activity Using Real-Time Tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(8) (August 2000)Google Scholar
  7. 7.
    Yang, Z.R., Zwolinski, M.: Mutual Information Theory for Adaptive Mixture Models. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(4) (April 2001)Google Scholar
  8. 8.
    Dempster, A., Laird, N., Rubin, D.: Maximum Likelihood From Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society 39(Series B), 1–38 (1977)zbMATHMathSciNetGoogle Scholar
  9. 9.
    Neal, R.M., Hinton, G.E.: A View of the EM Algorithm That Justifies Incremental, Sparse, and Other Variants. Learning in Graphical Models, 355–368 (1998)Google Scholar
  10. 10.
    Richardson, S., Green, P.J.: On Bayesian Analysis of Mixtures with an Unknown Number of Components. Journal of the Royal Statistical Society 60(Series B), 731–792 (1997)MathSciNetGoogle Scholar
  11. 11.
    KaewTraKulPong, P., Bowden, R.: An Adaptive Visual System for Tracking Low Resolution Colour Targets. In: Proceedings of British Machine Vision Conference 2001, vol. 1, pp. 243–252. Manchester, UK (September 2001)Google Scholar
  12. 12.
    Silveira Jacques Jr., J.C., Jung, C.R., Musse, S.R.: Background Subtraction and Shadow Detection in Grayscale Video Sequences. In: Proceedings of SIBGRAPI 2005-Natal-RN-Brazil (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rui Tan
    • 1
  • Hong Huo
    • 1
  • Jin Qian
    • 1
  • Tao Fang
    • 1
  1. 1.Institute of Image Processing and Pattern RecognitionShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations