Automation of Tracking Trajectories in a Crowded Situation


Studies on pedestrians using microscopic simulation require large amounts of trajectory data from real-world pedestrian crowds. The collection of such data, if done manually, involves tremendous efforts and is very time-consuming. Although many studies have asserted the possibility of automating this task using video cameras, we have found that only a few have demonstrated good performance in very crowded situations or from a top-angled view scene. This paper deals with tracking pedestrian crowd under heavy occlusion and from an angular scene using only a single non-stereo video camera. Our automated tracking system consists of three modules that are performed sequentially. The first module detects moving objects as blobs. The second module computes feature values from the blob information in order to generate what we call a possibility matrix. The third module is a tracking system, which employs a Bayesian update of the probability tree derived from the possibility matrix and from the detection of each pedestrian, in order to track the next position of the pedestrian. The result of such tracking is a database of pedestrian trajectories over time and space. With certain prior information, we show that the system is able to track a large number of people under occlusion and clutter scene.

This is a preview of subscription content, log in to check access.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10


  1. 1.

    Fruin, J.J., Pedestrian Planning and Design. Metropolitan Association of Urban Designers and Environmental Planners, Inc., New York (1971)

    Google Scholar 

  2. 2.

    TR (1985) Highway Capacity Manual, Special Report 204. Transportation Research Board, Washington D.C

    Google Scholar 

  3. 3.

    ITE (1994) Manual of Transportation Engineering Studies. Institute of Transportation Engineers, Prentice Hall, New Jersey

    Google Scholar 

  4. 4.

    Kluepfel HL (2003) A cellular automaton model for crowd movement and Egress simulation. Ph.D. Dissertation, Falkutät 4, Universität Duisburg-Essen

  5. 5.

    Teknomo K (2002) Microscopic pedestrian flow characteristics: development of an image processing data collection and simulation model. Ph.D. Dissertation, Tohoku University Japan, Sendai

  6. 6.

    McKenna, S. J.(2000) Tracking Groups of People. Computer Vision and Image Understanding 80:42–56

    Article  MATH  Google Scholar 

  7. 7.

    Kelly BAP (2007) Pedestrian detection and tracking using stereo vision techniques. PhD. Dissertation, Dublin City University, Dublin

  8. 8.

    Omar, J. and Mubarark, S.: Automated Multi-Camera Surveillance: Algorithm and Practice, Springer, New York (2008)

    Google Scholar 

  9. 9.

    Daamen W, Hoogendoorn SP (2003) Qualitative results from pedestrian laboratory experiments. In: Galea ER (ed) Pedestrian and evacuation dynamics 2003. CMS Press, London, pp 121–132

  10. 10.

    Leibe B, Seemann E, Schiele B (2005) Pedestrian detection in crowded scenes. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), pp 878–885

  11. 11.

    Kelly, P., O’Connor, N.E. and Smeaton, A.F.(2009) Robust pedestrian detection and tracking in crowded scenes. Image and Vision Computing 27:1445-1458

    Article  Google Scholar 

  12. 12.

    Saadat S, Teknomo K (2010) Automation of pedestrian tracking in a crowded situation. In: Proccedings of Fifth International Conference on Pedestrian and Evacuation Dynamics, Springer (in print)

  13. 13.

    Verestoy J, Chetverikov D (1998) Tracking feature points: a new algorithm. In: Proc 14th Int Conf on Pattern Recognition, Australia, pp 1436–1438

  14. 14.

    Chetverikov D, Verestoy J (1997) Motion tracking of dense feature point sets. In: Proc 21st Workshop of the Austrian Pattern Recognition Group. Oldenbourg Verlag, pp 233–242

  15. 15.

    Teknomo K, Takeyama Y, Inamura H (2000) Tracking algorithm for microscopic flow data collection. In: Proceeding of Japan Society of Civil Engineering (JSCE) Conference, Sendai, Japan

Download references


This project supported by Pedestrian Research Group of Ateneo De Manila University.

Author information



Corresponding author

Correspondence to Kardi Teknomo.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Saadat, S., Teknomo, K. & Fernandez, P. Automation of Tracking Trajectories in a Crowded Situation. Fire Technol 48, 73–90 (2012).

Download citation


  • Video tracking
  • Microscopic pedestrian
  • Occlusion