Neuro-Fuzzy Shadow Filter

  • Benny P. L. Lo
  • Guang-Zhong Yang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


In video sequence processing, shadow remains a major source of error for object segmentation. Traditional methods of shadow removal are mainly based on colour difference thresholding between the background and current images. The application of colour filters on MPEG or MJPEG images, however, is often erroneous as the chrominance information is significantly reduced due to compression. In addition, as the colour attributes of shadows and objects arc often very similar, discrete thresholding cannot always provide reliable results. This paper presents a novel approach for adaptive shadow removal by incorporating four different filters in a neuro-fuzzy framework. The neuro-fuzzy classifier has the ability of real-time self-adaptation and training, and its performance has been quantitatively assessed with both indoor and outdoor video sequences.


Grouping and segmentation neuro-fuzzy classifier shadow removal 


  1. 1.
    W. Lu and Y.P. Tan, “A Color Histogram Based People Tracking System”, IEEE Conf. On ISCAS2001, vol. 2, 137–140, 2001.Google Scholar
  2. 2.
    A. Prati, I. Mikić, C. Grana and M.M. Trivedi, “Shadow Detection Algorithms for Traffic Flow Analysis: a Comparative Study”, Proceedings of 2001 IEEE Intelligent Transportation Systems Conference Processings — Oakland (CA) USA, 340–345, 2001.Google Scholar
  3. 3.
    I. Mikić, P.C. Cosman, G.T. Kogut and M.M. Trivedi, “Moving Shadow and Object Detection in Traffic Scenes”, IEEE Proceedings of the 15 th International Conference on Pattern Recognition, vol. 1, 321–324, 2000.Google Scholar
  4. 4.
    C, Jiang and M.O. Ward, “Shadow Identification”, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1992 CVPR1992, 606–612, 1992.Google Scholar
  5. 5.
    P.L. Rosin and T. Ellis, “Image difference threshold strategies and shadow detection”, Proceedings of the 6 th British Machine Vision Conference, 347–356, 1995.Google Scholar
  6. 6.
    E. Salvador, A. Cavallaro and T. Ebrahimi, “Shadow Identification and Classification using Invariant Color Models”, Proceedings of the 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, 1545–1548, 2001.CrossRefGoogle Scholar
  7. 7.
    M. Kilger. “A Shadow Handler in a Video-based Real-time Traffic Monitoring System”, Proceedings of the IEEE Workshop on Applications of Computer Vision, 11–18, 1992.Google Scholar
  8. 8.
    Y. Sonoda and T. Ogata, “Separation of moving objects and their shadows, and application to tracking of loci in the monitoring images”, Proceedings of the 4 th International Conference on Signal Processing 1998, ICSP’ 98, vol. 2, 1261–1264, 1998.Google Scholar
  9. 9.
    K. Onoguchi, “Shadow Elimination Method for Moving Object Detection”, Proceedings of the 4 th International Conference on Pattern Recognition 1998, vol. 1, 583–587, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Benny P. L. Lo
    • 1
  • Guang-Zhong Yang
    • 1
  1. 1.Department of ComputingImperial College of Science, Technology and MedicineLondonUK

Personalised recommendations