An Automatic Traffic Surveillance System for Vehicle Tracking and Classification

  • Shih-Hao Yu
  • Jun-Wei Hsieh
  • Yung-Sheng Chen
  • Wen-Fong Hu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

This paper presents an automatic traffic surveillance system to estimate important traffic parameters from video sequences using only one camera. Different from traditional methods which classify vehicles into only cars and non-cars, the proposed method has a good capability to categorize cars into more specific classes with a new “linearity” feature. In addition, in order to reduce occlusions of vehicles, an automatic scheme of detecting lane dividing lines is proposed. With the found lane dividing lines, not only occlusions of vehicles can be reduced but also a normalization scheme can be developed for tackling the problems of feature size variations. Once all vehicle features are extracted, an optimal classifier is then designed to robustly categorize vehicles into different classes even though shadows, occlusions, and other noise exist. The designed classifier can collect different evidences from the database and the verified vehicle itself to make better decisions and thus much enhance the robustness and accuracy of classification. Experimental results show that the proposed method is much robust and powerful than other traditional methods.

Keywords

Kalman Filter Intelligent Transportation System Optimal Classifier Vehicle Detection Vehicle Tracking 
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.

References

  1. 1.
    D. Beymer, et al., “A real-time computer vision system for measure traffic parameters,” in Pro. IEEE Conf. CVPR, Puerto Rico, pp. 496–501, June 1997.Google Scholar
  2. 2.
    S. Gupte, et al., “Detection and classification of vehicles,” IEEE Transactions on ITS, vol. 3, no. 1, pp. 37–47, March 2002.Google Scholar
  3. 3.
    G. D. Sullivan, et al., “Model-based vehicle detection and classification using orthographic approximations,” Image Vision Computing, vol. 15, no. 8, pp.649–654, Aug. 1997.CrossRefGoogle Scholar
  4. 4.
    Y.-K. Jung, K.-W. Lee, and Y.-S. Ho, “Content-based event retrieval using semantic scene interpretation for automated traffic surveillance,” IEEE Transactions on ITS, vol. 2, no. 3, pp.151–163, Sept. 2001.Google Scholar
  5. 5.
    A. J. Lipton, et al., “Moving target classification and tracking from real-time video,” in Proc. IEEE Workshop Applications of Computer Vision, 1998, pp.8–14.Google Scholar
  6. 6.
    R. E. Kalman, “A new approach to linear filtering and prediction problems,” Transactions of the ASME-Journal of Basic Engineering, vol. 82, pp.35–45, March 1960.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Shih-Hao Yu
    • 1
  • Jun-Wei Hsieh
    • 1
  • Yung-Sheng Chen
    • 1
  • Wen-Fong Hu
    • 1
  1. 1.Department of Electrical EngineeringYuan Ze UniversityChung-LiTaiwan, R.O.C.

Personalised recommendations