Towards Robust Object Detection: Integrated Background Modeling Based on Spatio-temporal Features

  • Tatsuya Tanaka
  • Atsushi Shimada
  • Rin-ichiro Taniguchi
  • Takayoshi Yamashita
  • Daisaku Arita
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5994)


We propose a sophisticated method for background modeling based on spatio-temporal features. It consists of three complementary approaches: pixel-level background modeling, region-level one and frame-level one. The pixel-level background model uses the probability density function to approximate background model. The PDF is estimated non-parametrically by using Parzen density estimation. The region-level model is based on the evaluation of the local texture around each pixel while reducing the effects of variations in lighting. The frame-level model detects sudden, global changes of the the image brightness and estimates a present background image from input image referring to a background model image. Then, objects are extracted by background subtraction. Fusing their approaches realizes robust object detection under varying illumination, which is shown in several experiments.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Elgammal, A., et al.: Non-parametric model for background subtraction. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 751–767. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  2. 2.
    Toyama, K., et al.: Wallflower: Principle and practice of background maintenance. In: Proc. of Int. Conf. on Computer Vision, pp. 255–261 (1999)Google Scholar
  3. 3.
    Li, L., et al.: Statistical Modeling of complex background for foreground object detection. IEEE Tran. on Image Processing 13(11), 1459–1472 (2004)CrossRefGoogle Scholar
  4. 4.
    Satoh, Y., et al.: Robust object detection using a radial reach filter (RRF). Systems and Computers in Japan 35(10), 63–73 (2004)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Monari, E., et al.: Fusion of background estimation approaches for motion detection in non-static backgrounds. In: CD-ROM Proc. of IEEE Int. Conf. on Advanced Video and Signal Based Surveillance (2007)Google Scholar
  6. 6.
    Ukita, N.: Target-color learning and its detection for non-stationary scenes by nearest neighbor classification in the spatio-color space. In: Proc. of IEEE Int. Conf. on Advanced Video and Signal based Surveillance, pp. 394–399 (2005)Google Scholar
  7. 7.
    Stauffer, C., et al.: Adaptive background mixture models for real-time tracking. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, vol. 2, pp. 246–252 (1999)Google Scholar
  8. 8.
    Shimada, A., et al.: Dynamic control of adaptive mixture-of-gaussians background model. In: CD-ROM Proc. of IEEE Int. Conf. on Advanced Video and Signal Based Surveillance (2006)Google Scholar
  9. 9.
    Tanaka, T., et al.: A fast algorithm for adaptive background model construction using Parzen density estimation. In: CD-ROM Proc. of IEEE Int. Conf. on Advanced Video and Signal Based Surveillance (2007)Google Scholar
  10. 10.
    Zhang, S., et al.: Dynamic background modeling and subtraction using spatio-temporal local binary patterns. In: Proc. of IEEE Int. Conf. on Image Processing, pp. 1556–1559 (2008)Google Scholar
  11. 11.
    Fukui, S., et al.: Extraction of moving objects by estimating background brightness. Journal of the Institue of Image Electronics Engineers of Japan 33(3), 350–357 (2004)Google Scholar
  12. 12.
    Tanaka, T., et al.: Non-parametric background and shadow modeling for object detection. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part I. LNCS, vol. 4843, pp. 159–168. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Tatsuya Tanaka
    • 1
  • Atsushi Shimada
    • 1
  • Rin-ichiro Taniguchi
    • 1
  • Takayoshi Yamashita
    • 2
  • Daisaku Arita
    • 1
    • 3
  1. 1.Kyushu UniversityFukuokaJapan
  2. 2.OMRON Corp. KyotoJapan
  3. 3.Institute of Systems, Information Technologies and Nanotechnologies (ISIT)FukuokaJapan

Personalised recommendations