Enhanced Codebook Model for Real-Time Background Subtraction

  • Munir Shah
  • Jeremiah Deng
  • Brendon Woodford
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7064)


The CodeBook is one of the popular real-time background models for moving object detection in a video. However, for some of the complex scenes, it does not achieve satisfactory results due to the lack of an automatic parameters estimation mechanism. In this paper, we present an improved CodeBook model, which is robust in sudden illumination changes and quasi-periodic motions. The major contributions of the paper are a robust statistical parameter estimation method, a controlled adaptation procedure, a simple, but effective technique to suppress shadows and a novel block based approach to utilize the local spatial information. The proposed model was tested on numerous complex scenes and results shows a significant performance improvement over standard model.


Codebook Video Segmentation Background Subtraction Mixture of Gaussians On line Learning Online Clustering 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Doshi, A., Trivedi, M.: Hybrid cone-cylinder codebook model for foreground detection with shadow and highlight suppression. In: IEEE International Conference on Video and Signal Based Surveillance, AVSS 2006, pp. 19–29 (2006)Google Scholar
  2. 2.
    Zivkovic, Z.: Improved adaptive gaussian mixture model for background subtraction. In: 17th International Conference on Pattern Recognition (ICPR 2004), vol. 2, pp. 28–31. IEEE Computer Society, Washington, DC, USA (2004)Google Scholar
  3. 3.
    Huang, T., Qiu, J., Ikenaga, T.: A foreground extraction algorithm based on adaptively adjusted gaussian mixture models. In: Fifth International Joint Conference on INC, IMS and IDC, pp. 1662–1667 (2009)Google Scholar
  4. 4.
    Darvish, P., Sills-Lavoie, M., Bilodeau, G.A.: A multiscale region-based motion detection and background subtraction algorithm. Sensors 10(2), 1041–1061 (2010)CrossRefGoogle Scholar
  5. 5.
    Kim, K., Chalidabhongse, T.H., Harwood, D., Davis, L.: Real-time foreground-background segmentation using codebook model. J. Real-Time Imaging 11, 172–185 (2005)CrossRefGoogle Scholar
  6. 6.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252 (1999)Google Scholar
  7. 7.
    Cheng, J., Yang, J., Zhou, Y.: A novel adaptive gaussian mixture model for background subtraction. In: Proceeding of 2nd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 2005), Shanghai, China, pp. 587–593 (2005)Google Scholar
  8. 8.
    Friedman, N., Russel, S.: Image segmentation in a video sequences: A probabilistic approach. In: Proceeding of Thirteen Conference on Uncertainty in Artificial Intelligence, pp. 175–181 (1997)Google Scholar
  9. 9.
    Mahadevan, V., Vasconcelos, N.: Background subtraction in highly dynamic scenes. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–6 (2008)Google Scholar
  10. 10.
    Kim, H., et al.: Background subtraction using generalized gaussian family model. IEEE Electronics Letters 24(5), 473–482 (2006)Google Scholar
  11. 11.
    Cheng, J., Yang, J., Zhou, Y., Cui, Y.: Flexible background mixture models for foreground segmentation. J. Image and Vision Computing 24(5), 473–482 (2006)CrossRefGoogle Scholar
  12. 12.
    Zhong, J., Sclaroff, S.: Segmenting foreground objects from a dynamic textured background via a robust kalman filter. In: Proceeding of Ninth IEEE International Conference on Computer Vision (ICCV 2003), Washington, DC, USA, p. 44 (2003)Google Scholar
  13. 13.
    White, B., Shah, M.: Automatically tunings background subtraction parameters using particle swarm optimization. In: Proceeding of IEEE International Conference on Multimedia and Expo. (2005)Google Scholar
  14. 14.
    Figueiredo, M.A.T., Jain, A.K.: Unsupervised learning of finite mixture models. J. IEEE Transaction on Pattern Analysis and Machine Intelligence 24(3), 381–396 (2000)CrossRefGoogle Scholar
  15. 15.
    Herrero, S., Bescos, J.: Background Subtraction Techniques: Systematic Evaluation and Comparative Analysis. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2009. LNCS, vol. 5807, pp. 33–42. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  16. 16.
    Lee, D.-S.: Effective gaussian mixture learning for video background subtraction. J. IEEE Transactions on Pattern Analysis and Machine Intelligence 27, 827–832 (2005)CrossRefGoogle Scholar
  17. 17.
    Guo, J.-M., Hsu, C.-S.: Cascaded background subtraction using block-based and pixel-based codebooks. In: Proceedings of the 2010 20th International Conference on Pattern Recognition, ICPR 2010, pp. 1373–1376 (2010)Google Scholar
  18. 18.
    Wu, M., Peng, X.: Spatio-temporal context for codebook-based dynamic background subtraction. AEU - International Journal of Electronics and Communications 64(8), 739–747 (2010)CrossRefGoogle Scholar
  19. 19.
    Kentaro, T., John, K., Barry, B., Brian, M.: Wallflower: Principles and practice of background maintenance. In: IEEE International Conference on Computer Vision (CCV 2009), p. 255 (1999)Google Scholar
  20. 20.
    Piccardi, M.: Background subtraction techniques: a review. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 4, pp. 3099–3104 (2004)Google Scholar
  21. 21.
    Wu, Y., Zeng, D., Li, H.: Layered video objects detection based on lbp and codebook. In: First International Workshop on Education Technology and Computer Science, vol. 1, pp. 207–213 (2009)Google Scholar
  22. 22.
    Li, Y., Chen, F., Xu, W., Du, Y.: Gaussian-Based Codebook Model for Video Background Subtraction. In: Jiao, L., Wang, L., Gao, X.-b., Liu, J., Wu, F. (eds.) ICNC 2006. LNCS, vol. 4222, pp. 762–765. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Munir Shah
    • 1
  • Jeremiah Deng
    • 1
  • Brendon Woodford
    • 1
  1. 1.Department of Information ScienceUniversity of OtagoDunedinNew Zealand

Personalised recommendations