A Novelty Detection Approach for Foreground Region Detection in Videos with Quasi-stationary Backgrounds

  • Alireza Tavakkoli
  • Mircea Nicolescu
  • George Bebis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4291)


Detecting regions of interest in video sequences is one of the most important tasks in many high level video processing applications. In this paper a novel approach based on support vector data description is presented, which detects foreground regions in videos with quasi-stationary backgrounds. The main contribution of this paper is the novelty detection approach which automatically segments video frames into background/foreground regions. By using support vector data description for each pixel, the decision boundary for the background class is modeled without the need to statistically model its probability density function. The proposed method is able to achieve very accurate foreground region detection rates even in very low contrast video sequences, and in the presence of quasi-stationary backgrounds. As opposed to many statistical background modeling approaches, the only critical parameter that needs to be adjusted in our method is the number of background training frames.


Video Sequence Kernel Density Estimation Decision Boundary Recall Rate False Reject Rate 
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.
    Pless, R., Larson, J., Siebers, S., Westover, B.: Evaluation of local models of synamic backgrounds. In: Proceedings of the CVPR, vol. 2, pp. 73–78 (2003)Google Scholar
  2. 2.
    Elgammal, A., Duraiswami, R., Harwood, D., Davis, L.: Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE 90, 1151–1163 (2002)CrossRefGoogle Scholar
  3. 3.
    Pless, R., Brodsky, T., Aloimonos, Y.: Detecting independent motion: The statistics of temporal continuity. IEEE Transactions on PAMI 22, 68–73 (2000)Google Scholar
  4. 4.
    Wern, C., Azarbayejani, A., Darrel, T., Petland, A.: Pfinder: real-time tracking of human body. IEEE Transactions on PAMI 19, 780–785 (1997)Google Scholar
  5. 5.
    Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principels and practive of background maintenance. In: Proceedings of ICCV, vol. 1, pp. 255–261 (1999)Google Scholar
  6. 6.
    Koller, D., Huang, J.W.T., Malik, J., Ogasawara, G., Rao, B., Russel, S.: Towards robust automatic traffic scene analysis in real-time. In: ICPR, vol. 1, pp. 126–131 (1994)Google Scholar
  7. 7.
    Stauffer, C., Grimson, W.: Learning patterns of activity using real-time tracking. IEEE Transactions on PAMI 22, 747–757 (2000)Google Scholar
  8. 8.
    Friedman, N., Russell, S.: Image segmentation in video sequences: A probabilistic approach. In: Annual Conference on Uncertainty in Artificial Intelligence, pp. 175–181 (1997)Google Scholar
  9. 9.
    McKenna, S., Raja, Y., Gong, S.: Object tracking using adaptive color mixture models. In: Proceedings of Asian Conferenc on Computer Vision, vol. 1, pp. 615–622 (1998)Google Scholar
  10. 10.
    Lee, D.S.: Effective gaussian mixture learning for video background subtraction. IEEE Transactions on PAMI 27, 827–832 (2005)Google Scholar
  11. 11.
    Mittal, A., Paragios, N.: Motion-based background subtraction using adaptive kernel density estimation. In: Proceedings of CVPR, vol. 2, pp. 302–309 (2004)Google Scholar
  12. 12.
    Kim, K., Harwood, D., Davis, L.S.: Background updating for visual surveillance. In: Proceedings of the International Symposium on Visual Computing, vol. 1, pp. 337–346 (2005)Google Scholar
  13. 13.
    Tavakkoli, A., Nicolescu, M., Bebis, G.: Automatic robust background modeling using multivariate non-parametric kernel density estimation for visual surveillance. In: Bebis, G., Boyle, R., Koracin, D., Parvin, B. (eds.) ISVC 2005. LNCS, vol. 3804, pp. 363–370. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  14. 14.
    Tax, D.M.J., Duin, R.P.: Support vector data description. Machine Learning 54, 45–66 (2004)MATHCrossRefGoogle Scholar
  15. 15.
    Tax, D.: Ddtools, the data description toolbox for matlab, version 1.11 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alireza Tavakkoli
    • 1
  • Mircea Nicolescu
    • 1
  • George Bebis
    • 1
  1. 1.Computer Vision Lab., Department of Computer Science and EngineeringUniversity of NevadaRenoUSA

Personalised recommendations