Non-parametric Background and Shadow Modeling for Object Detection

  • Tatsuya Tanaka
  • Atsushi Shimada
  • Daisaku Arita
  • Rin-ichiro Taniguchi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4843)


We propose a fast algorithm to estimate background models using Parzen density estimation in non-stationary scenes. Each pixel has a probability density which approximates pixel values observed in a video sequence. It is important to estimate a probability density function fast and accurately. In our approach, the probability density function is partially updated within the range of the window function based on the observed pixel value. The model adapts quickly to changes in the scene and foreground objects can be robustly detected. In addition, applying our approach to cast-shadow modeling, we can detect moving cast shadows. Several experiments show the effectiveness of our approach.


Gaussian Mixture Model Object Detection Background Model Foreground Object Foreground Pixel 
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.
    Han, B., Comaniciu, D., Davis, L.: Sequential Kernel Density Approximation through Mode Propagation: Applications to Background Modeling. In: Asian Conference on Computer Vision 2004, pp. 818–823 (2004)Google Scholar
  2. 2.
    Elgammal, A., Duraiswami, R., Harwood, D., Davis, L.S.: Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance. In: Proceedings of the IEEE, vol. 90, pp. 1151–1163 (2002)Google Scholar
  3. 3.
    Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: Principle and Practice of Background Maintenance. In: International Conference on Computer Vision, pp. 255–261 (1999)Google Scholar
  4. 4.
    Harville, M.: A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Background Models. In: the 7th European Conference on Computer Vision, vol. III, pp. 543–560 (2002)Google Scholar
  5. 5.
    Lee, D.-S.: Online Adaptive Gaussian Mixture Learning for Video Applications. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 105–116. Springer, Heidelberg (2004)Google Scholar
  6. 6.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. Computer Vision and Pattern Recognition 2, 246–252 (1999)Google Scholar
  7. 7.
    Shimada, A., Arita, D., Taniguchi, R.i.: Dynamic Control of Adaptive Mixture-of-Gaussians Background Model. In: Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance 2006 (2006)Google Scholar
  8. 8.
    Salvador, E., Cavallaro, A., Ebrahimi, T.: SHADOW IDENTIFICATION AND CLASSIFICATION USING INVARIANT COLOR MODELS. In: Proc. of IEEE International Conference on Acoustics, vol. 3, pp. 1545–1548 (2001)Google Scholar
  9. 9.
    Cucchiara, R., Grana, C., Piccardi, M., Prati, A., Sirotti, S.: Improving Shadow Suppression in Moving Object Detection with HSV Color Information. In: IEEE Intelligent Transportation Systems Conference Proceedings, pp. 334–339 (2001)Google Scholar
  10. 10.
    Schreer, O., Feldmann, I., Golz, U., Kauff, P.: FAST AND ROBUST SHADOW DETECTION IN VIDEOCONFERENCE APPLICATION. 4th IEEE Intern. Symposium on Video Proces. and Multimedia Comm, 371–375 (2002)Google Scholar
  11. 11.
    Bevilacqua, A.: Effective Shadow Detection in Traffic Monitoring Applications. In: The 11th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (2003)Google Scholar
  12. 12.
    Martel-Brisson, N., Zaccarin, A.: Moving Cast Shadow Detection from a Gaussian Mixture Shadow Model. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition  (2005)Google Scholar
  13. 13.
    Parzen, E.: On the estimation of a probability density function and mode. The Annals of Mathematical Statistics 33(3), 1065–1076 (1962)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Tatsuya Tanaka
    • 1
  • Atsushi Shimada
    • 1
  • Daisaku Arita
    • 1
    • 2
  • Rin-ichiro Taniguchi
    • 1
  1. 1.Department of Intelligent Systems, Kyushu University, 744, Motooka, Nishi-ku, Fukuoka 819–0395Japan
  2. 2.Institute of Systems & Information Technologies/KYUSHU, 2–1–22, Momochihama, Sawara-ku, Fukuoka 814–0001Japan

Personalised recommendations