A Kalman Filter Based Background Updating Algorithm Robust to Sharp Illumination Changes

  • Stefano Messelodi
  • Carla Maria Modena
  • Nicola Segata
  • Michele Zanin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3617)


A novel algorithm, based on Kalman filtering is presented for updating the background image within video sequences. Unlike existing implementations of the Kalman filter for this task, our algorithm is able to deal with both gradual and sudden global illumination changes. The basic idea is to measure global illumination change and to use it as an external control of the filter. This allows the system to better fit the assumptions about the process to be modeled. Moreover, we propose methods to estimate measurement noise variance and to deal with the problem of saturated pixels, to improve the accuracy and robustness of the algorithm. The algorithm has been successfully tested in a traffic surveillance task by comparing it to a background updating algorithm, based on Kalman filtering, taken from literature.


Background Image Illumination Change Foreground Object Foreground Pixel Global Illumination 
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.


  1. 1.
    Kalman, R.E.: A New Approach to Linear Filtering and Prediction Problems. Transactions of the ASME Journal of Basic Engineering 82(Series D), 35–45 (1960)Google Scholar
  2. 2.
    Karman, K., Brandt, A., Gerl, R.: Moving object segmentation based on adaptive reference images. In: Signal Processing V: Theories and Applications, Barcelona, Spain, September 1990, pp. 951–954 (1990)Google Scholar
  3. 3.
    Boninsegna, M., Bozzoli, A.: A Tunable Algorithm to Update a Reference Image. Signal Processing: Image Communication 16(4), 353–365 (2000)CrossRefGoogle Scholar
  4. 4.
    Koller, D., Weber, J., Huang, T., Malik, J., Ogasawara, G., Rao, B., Russell, S.: Toward robust automatic traffic scene analyis in real-time. In: Proc. Int. Conf. Pattern Recognition, pp. 126–131 (1994)Google Scholar
  5. 5.
    Catlin, D.E.: Estimation, control, and the discrete Kalman filter. Springer, Heidelberg (1989)zbMATHGoogle Scholar
  6. 6.
    Oppenheim, A.V., Schafer, R.W., Stockham Jr., T.G.: Nonlinear filtering of multiplied and convolved signals. Proc. IEEE 56, 1264–1291 (1968)CrossRefGoogle Scholar
  7. 7.
    Messelodi, S., Modena, C.M., Zanin, M.: A computer vision system for the detection and classification of vehicles at urban road intersections. ITC-irst Technical Report T04-02-07 (February 2004)Google Scholar
  8. 8.
    Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, P.: Pfinder: Real-time tracking of human body. IEEE Transaction PAMI 19, 780–785 (1997)Google Scholar
  9. 9.
    Grimson, W.E.L., Stauffer, C.: Adaptive background mixture models for real-time tracking. In: Proc. IEEE Computer Vision Pattern Recognition, vol. 1, pp. 22–29 (1999)Google Scholar
  10. 10.
    Elgammal, A., Duraiswami, R., Harwood, D., Davis, L.S.: Background and foreground modeling using nonparametric kernel density estimation for video surveillance. Proc. of the IEEE 90(7), 1151–1163 (2002)CrossRefGoogle Scholar
  11. 11.
    Li, L., Huang, W., Gu, I., Tian, Q.: Statistical modeling of complex backgrounds for foreground object detection. IEEE Trans. Image Processing 13 (November 2004)Google Scholar
  12. 12.
    Li, L., Leung, M.: Integrating intensity and texture differences for robust change detection. IEEE Trans. Image Processing 11, 105–112 (2002)CrossRefGoogle Scholar
  13. 13.
    Wixson, L.: Detecting salient motion by accumulating directionary-consistent flow. IEEE Trans. PAMI 22, 269–274 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Stefano Messelodi
    • 2
  • Carla Maria Modena
    • 2
  • Nicola Segata
    • 1
  • Michele Zanin
    • 2
  1. 1.University of TrentoItaly
  2. 2.ITC-irstPovo (Trento)Italy

Personalised recommendations