Scene Context Modeling for Foreground Detection from a Scene in Remote Monitoring

  • Liyuan Li
  • Xinguo Yu
  • Weimin Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4842)


In this paper, foreground detection is performed by scene interpretation. A natural scene in different illumination conditions is characterized by scene context which contains spatial and appearance representations. The spatial representation is obtained in two steps. First, the large homogenous regions in each sample image are extracted using local and global dominant color histograms (DCH). Then, the latent semantic regions of the scene are generated by combining the coincident regions in the segmented images. The appearance representation is learned by the probabilistic latent semantic analysis (PLSA) model with local DCH visual words. The scene context is then applied to interpret incoming images from the scene. For a new image, its global appearance is first recognized and then the pixels are labelled under the constraint of the scene appearance. The proposed method has been tested on various scenes under different weather conditions and very promising results have been obtained.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wren, C., Azarbaygaui, A., Darrell, T., Pentland, A.: Pfinder: Real-time tracking of the human body. IEEE Trans. Pattern Analy. and Mach. Intel. 19, 780–785 (1997)CrossRefGoogle Scholar
  2. 2.
    Haritaoglu, I., Harwood, D., Davis, L.: W4: Real-time surveillance of people and their activities. IEEE Trans. Pattern Analy. and Mach. Intel. 22, 809–830 (2000)CrossRefGoogle Scholar
  3. 3.
    Stauffer, C., Grimson, W.: Learning patterns of activity using real-time tracking. IEEE Trans. Pattern Analy. and Mach. Intel. 22, 747–757 (2000)CrossRefGoogle Scholar
  4. 4.
    Li, L., Huang, W., Gu, I., Tian, Q.: Statistical modeling of complex background for foreground object detection. IEEE Trans. Image Processing 13, 1459–1472 (2004)CrossRefGoogle Scholar
  5. 5.
    Konishi, S., Yuille, A.: Statistical cues for domain specific image segmentation with performance analysis. In: IEEE CVPR, pp. 291–301 (2000)Google Scholar
  6. 6.
    Li, L., Luo, R., Huang, W., Eng, H.L.: Context-controlled adaptive background subtraction. In: IEEE Workshop on PETS, pp. 31–38 (2006)Google Scholar
  7. 7.
    Comanicu, D., Meer, P.: Mean-shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Analy. and Mach. Intel. 24, 603–619 (2002)CrossRefGoogle Scholar
  8. 8.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. In: IEEE CVPR, pp. 731–743 (1997)Google Scholar
  9. 9.
    Li, F., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE CVPR, vol. 2, pp. 524–531 (2005)Google Scholar
  10. 10.
    Quelhas, P., Monay, F., Odobez, J.M., Gatica-Perez, D., Tuytelaaars, T., Van Gool, L.: Modeling scenes with local descriptors and latent aspects. In: IEEE ICCV, vol. 1, pp. 883–890 (2005)Google Scholar
  11. 11.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering objects and their location in images. In: IEEE ICCV (2005)Google Scholar
  12. 12.
    Hofmann, T.: Unsupervised learning by probabilistic latent semantic analysis. Machine Learning 42, 177–196 (2001)zbMATHCrossRefGoogle Scholar
  13. 13.
    Alexander, D., Buxton, B.: Statistical modeling of colour data. Int’l J. Computer Vision 44, 87–109 (2001)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Liyuan Li
    • 1
  • Xinguo Yu
    • 1
  • Weimin Huang
    • 1
  1. 1.Institute for Infocomm ResearchSingapore

Personalised recommendations