The Study of the Detection and Tracking of Moving Pedestrian Using Monocular-Vision

  • Chang Hao-li
  • Shi Zhong-ke
  • Fu Qing-hua
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3994)


To ensure the safety and efficiency of the pedestrian traffic, this paper presents a real-time system for moving pedestrian detection and tracking in sequences of images of outdoor scenes acquired by a stationary camera. The self-adaptive background subtraction method and the dynamic multi-threshold method were adopted here for background subtraction and image segmentation. During the process of tracking, a new method based on gray model GM(1,1) was proposed to predict the motion of pedestrians. And then a template for tracking pedestrian continuously was presented by fusing several characters of targets. Experimental results of two real urban traffic scenes demonstrate the efficiency of this method, then the application of this method is discussed in real transportation system.


Difference Image Current Image Current Background Stationary Camera Pedestrian Detection 
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.
    Chu, J.W., Ji, L.S., Guo, L., et al.: Study on Method of Detecting Preceding Vehicle Based on Monocular Camera. In: IEEE Intelligent Vehicles, Italy, June 14-17, pp. 750–755 (2004)Google Scholar
  2. 2.
    Surendra, G., Osama, M., Robert, F., et al.: Detection and Classification of Vehicles. IEEE Transactions on Intelligent Transportation Systems 3(1), 37–47 (2002)CrossRefGoogle Scholar
  3. 3.
    Osama, M., Nikolaos, P.P.: A novel method for tracking and counting pedestrians in real-time using a single camera. IEEE Transactions on Vehicles Technology (2001)Google Scholar
  4. 4.
    Wohle, J.C., Anlauf, J., Pörtner, T., et al.: A time delay neural network algorithm for real-time pedestrian recognition. In: IEEE Intelligent Vehicles, pp. 247–252 (1998)Google Scholar
  5. 5.
    Zhao, L., Thorpe, C.: Stereo and neural network-based pedestrian detection. In: ITSC, pp. 289–303 (1999)Google Scholar
  6. 6.
    Pai, C.J., Tyan, H.R., Liang, Y.M.: Pedestrian detection and tracking at crossroads, pp. 101–104. IEEE, Los Alamitos (2003)Google Scholar
  7. 7.
    Cristovbal, C., Johann, E., Thomas, K.: Walking pedestrian recognition. IEEE Transactions on Intelligent Transportation Systems 3(1), 155–163 (2000)Google Scholar
  8. 8.
    Alan, J.L., Hironobu, F., Raju, S.P.: Moving target classification and tracking from real-time video, pp. 8–14. IEEE, Los Alamitos (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Chang Hao-li
    • 1
  • Shi Zhong-ke
    • 1
  • Fu Qing-hua
    • 1
  1. 1.College of AutomationNorthwestern Polytechnical UniversityXi’anChina

Personalised recommendations