Machine Vision and Applications

, Volume 20, Issue 6, pp 395–409 | Cite as

Non-parametric statistical background modeling for efficient foreground region detection

  • Alireza Tavakkoli
  • Mircea Nicolescu
  • George Bebis
  • Monica Nicolescu
Original Paper

Abstract

Most methods for foreground region detection in videos are challenged by the presence of quasi-stationary backgrounds—flickering monitors, waving tree branches, moving water surfaces or rain. Additional difficulties are caused by camera shake or by the presence of moving objects in every image. The contribution of this paper is to propose a scene-independent and non-parametric modeling technique which covers most of the above scenarios. First, an adaptive statistical method, called adaptive kernel density estimation (AKDE), is proposed as a base-line system that addresses the scene dependence issue. After investigating its performance we introduce a novel general statistical technique, called recursive modeling (RM). The RM overcomes the weaknesses of the AKDE in modeling slow changes in the background. The performance of the RM is evaluated asymptotically and compared with the base-line system (AKDE). A wide range of quantitative and qualitative experiments is performed to compare the proposed RM with the base-line system and existing algorithms. Finally, a comparison of various background modeling systems is presented as well as a discussion on the suitability of each technique for different scenarios.

Keywords

Non-parametric density estimation Recursive modeling Background subtraction Background modeling Quasi-stationary backgrounds 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Criminisi, C., Gross, G., Blake, A., Kolmogorov, V.: Bilayer segmentation of live video. In: Proceedings of the CVPR pp. 17–22 (2006)Google Scholar
  2. 2.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, New York (2001)MATHGoogle Scholar
  3. 3.
    Elgammal, A., Duraiswami, R., Davis, L.S.: Efficient computation of kernel density estimation using fast Gauss transform with application for segmentation and tracking. In: Proceedings of the 2nd IEEE International Workshop on Statistical and Computational Theories of Vision (2001)Google Scholar
  4. 4.
    Elgammal, A., Duraiswami, R., Davis, L.S.: Efficient non-parametric adaptive color modeling using fast Gauss transform. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (2001)Google Scholar
  5. 5.
    Elgammal, A., Duraiswami, R., Harwood, D., Davis, L.: Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proc. IEEE 90, 1151–1163 (2002)CrossRefGoogle Scholar
  6. 6.
    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
  7. 7.
    Hsu, Y., Nagel, H., Rekers, G.: New likelihood test methods for change detection in image sequences. Comput. Vis. Graph. Image Process. 26, 73–106 (1984)CrossRefGoogle Scholar
  8. 8.
    Indupalli, S., Ali, M., Boufama, B.: A novel clustering-based method for adaptive background segmentation. In: Proceedings of the Computer and Robot Vision, pp. 37–43 (2006)Google Scholar
  9. 9.
    Karman, K.P., von Brandt, A.: Moving object recognition using an adaptive background memory. In: Proc. Time-varying Image Processing and Moving Object Recognition (1990)Google Scholar
  10. 10.
    Karman, K.P., von Brandt, A.: Moving object segmentation based on adaptive reference images. In: Signal Processing: Theories and Applications, pp. 951–954 (1990)Google Scholar
  11. 11.
    Kim, K., Harwood, D., Davis, L.S.: Background updating for visual surveillance. Proc. Int. Symp. Vis. Comput. 1, 337–346 (2005)Google Scholar
  12. 12.
    Koller, D., Weber, J., Huang, T., Malik, J., Ogasawara, G., Rao, B., Russel, S.: Towards Robust Automatic Traffic Scene Analysis in Real-Time. In proceedings of ICPR 1, 126–131 (1994)Google Scholar
  13. 13.
    Lee, D.S.: Effective Gaussian mixture learning for video background subtraction. IEEE Trans. PAMI 27(5), 827–832 (2005)Google Scholar
  14. 14.
    Li, L., Huang, W., Gu, I., Tian, Q.: Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans. Image Process. 13(11), 1459–1472 (2004)CrossRefGoogle Scholar
  15. 15.
    Matsuyama, T., Ohya, T., Habe, H.: Background subtraction for non-stationary scenes. In: Proceedings of Asian Conference on Computer Vision, pp. 662–667 (2000)Google Scholar
  16. 16.
    McKenna, S., Raja, Y., Gong, S.: Object tracking using adaptive color mixture models. Proc. Asian Conf. Comput. Vis. 1, 615–622 (1998)Google Scholar
  17. 17.
    McKenna, S., Raja, Y., Gong, S.: Tracking colour objects using adaptive mixture models. Image Vis. Comput. 17, 223–229 (1999)CrossRefGoogle Scholar
  18. 18.
    Mittal, A., Paragios, N.: Motion-based background subtraction using adaptive kernel density estimation. Proc. CVPR 2, 302–309 (2004)Google Scholar
  19. 19.
    Paragios, N., Ramesh, V.: A MRF-based approach for real-time subway monitoring. IEEE Trans. PAMI 1, 1030–1040 (2001)Google Scholar
  20. 20.
    Pless, R., Brodsky, T., Aloimonos, Y.: Detecting independent motion: the statistics of temporal continuity. IEEE Trans. PAMI 22(8), 68–73 (2000)Google Scholar
  21. 21.
    Pless, R., Larson, J., Siebers, S., Westover, B.: Evaluation of local models of dynamic backgrounds. Proc. CVPR 2, 73–78 (2003)Google Scholar
  22. 22.
    Rittscher, J., Kato, J., Joga, S., Blake, A.: A probabilistic background model for tracking. Proc. 6th Eur. Conf. Comput. Vision 1843, 336–350 (2000)Google Scholar
  23. 23.
    Sheikh, Y., Shah, M.: Bayesian object detection in dynamic scenes. Proc. CVPR 1, 74–79 (2005)Google Scholar
  24. 24.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. Proc. CVPR 2, 246–252 (1999)Google Scholar
  25. 25.
    Stauffer, C., Grimson, W.: Learning patterns of activity using real-time tracking. IEEE Trans. PAMI 22(8), 747–757 (2000)Google Scholar
  26. 26.
    Stenger, B., Ramesh, V., Paragios, N., Coetzee, F., Buhmann, J.: A probabilistic background model for tracking. In Proceedings of ICCV, pp. 294–301 (2001)Google Scholar
  27. 27.
    Tavakkoli, A., Nicolescu, M., Bebis, G.: Automatic robust background modeling using multivariate non-parametric kernel density estimation for visual surveillance. In: Proceedings of the International Symposium on Visual Computing, LNSC, vol. 3804, pp. 363–370 (2005)Google Scholar
  28. 28.
    Tavakkoli, A., Nicolescu, M., Bebis, G.: Automatic statistical object detection for visual surveillance. In: Proceedings of IEEE Southwest Symposium on Image Analysis and Interpretation, pp. 144–148 (2006)Google Scholar
  29. 29.
    Tavakkoli, A., Nicolescu, M., Bebis, G.: Robust recursive learning for foreground region detection in videos with quasi-stationary backgrounds. In proceedings of 18th International Conference on Pattern Recognition (2006)Google Scholar
  30. 30.
    Totozafiny, T., Patrouix, O., Luthon, F., Coutllier, J.: Dynamic background segmentation for remote reference image updating within motion detection JPG2000. In: Proceedings of the International Symposium on Industrial Electronics, pp. 505–510 (2006)Google Scholar
  31. 31.
    Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principles and practice of background maintenance. Proc. ICCV 1, 255–261 (1999)Google Scholar
  32. 32.
    Wern, C., Azarbayejani, A., Darrel, T., Petland, A.: Pfinder: real-time tracking of human body. IEEE Trans. PAMI 19(7), 780–785 (1997)Google Scholar
  33. 33.
    Wixson, L.: Detecting salient motion by accumulating directionary-consistent flow. IEEE Trans. Pattern Anal. Mach. Intell. 22, 774–780 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  • Alireza Tavakkoli
    • 1
  • Mircea Nicolescu
    • 1
  • George Bebis
    • 1
  • Monica Nicolescu
    • 2
  1. 1.Computer Vision LabUniversity of NevadaRenoUSA
  2. 2.Robotics LaboratoryUniversity of NevadaRenoUSA

Personalised recommendations