Automatic Estimation of Movement Statistics of People

  • Thomas Jensen
  • Henrik Rasmussen
  • Thomas B. Moeslund
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7378)


Automatic analysis of how people move about in a particular environment has a number of potential applications. However, no system has so far been able to do detection and tracking robustly. Instead, trajectories are often broken into tracklets. The key idea behind this paper is based around the notion that people need not be detected and tracked perfectly in order to derive useful movement statistics for a particular scene. Tracklets will suffice. To this end we build a tracking framework based on a HoG detector and an appearance-based particle filter. The detector is optimized by learning a scene model allowing for a speedup of the process together with a significantly reduced false positive rate. The developed system is applied in two different scenarios where it is shown that useful statistics can indeed be extracted.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Poulsen, E., Andersen, H., Gade, R., Jensen, O., Moeslund, T.: Using Human Motion Intensity as Input for Urban Design. In: Workshop on Interactive Human Behavior Analysis in Open or Public Spaces, Amsterdam, Holland (2011)Google Scholar
  2. 2.
    Christensen, P., Mikkelsen, M.R., Alexander, T., Nielsen, S., Harder, H.: Children, Mobility and Space: Using GPS and Mobile Phone Technologies in Ethnographic Research. Journal of Mixed Methods Research 5, 227–246 (2011)CrossRefGoogle Scholar
  3. 3.
    Moeslund, T., Hilton, A., Kruger, V., Sigal, L. (eds.): Visual Analysis of Humans Looking at people. Springer (2011)Google Scholar
  4. 4.
    Kuo, C.H., Huang, C., Nevatia, R.: Multi-target tracking by Online Learned Discriminative Appearance Models. In: Computer Vision and Pattern Recognition, San Francisco, CA, USA (2010)Google Scholar
  5. 5.
    Babenko, B., Yang, M.H., Belongie, S.: Visual tracking with online Multiple Instance Learning. In: Computer Vision and Pattern Recognition (2009)Google Scholar
  6. 6.
    Moore, B., Ali, S., Mehran, R., Shah, M.: Visual Crowd Surveillance through a Hydrodynamics Lens. Communications of the ACM 54, 64–73 (2011)CrossRefGoogle Scholar
  7. 7.
    Pellegrini, S., Ess, A., Van Gool, L.: Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 452–465. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Breitenstein, M.D., Reichlin, F., Leibe, B., Koller-Meier, E., Gool, L.V.: Online Multi-Person Tracking-by-Detection from a Single, Uncalibrated Camera. IEEE Transactions on Pattern Analysis and Machine Intelligence (in press)Google Scholar
  9. 9.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: Computer Vision and Pattern Recognition (2005)Google Scholar
  10. 10.
    Grabner, H., Bischof, H.: Online Boosting and Vision. In: Computer Vision and Pattern Recognition, New York, NY, USA (2006)Google Scholar
  11. 11.
    Jensen, T., Rasmussen, H.: Automatic Estimation of Statistics on the Movement of People in Complex Indoor Scenes. Master’s thesis. Aalborg University (2011)Google Scholar
  12. 12.
    Flores, B.E.: A Pragmatic View of Accuracy Measurement in Forecasting. Omega 14, 93–98 (1986)CrossRefGoogle Scholar
  13. 13.
    Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: The CLEAR MOT metrics. Journal on Image and Video Processing, 1–10 (February 2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Thomas Jensen
    • 1
  • Henrik Rasmussen
    • 1
  • Thomas B. Moeslund
    • 1
  1. 1.Visual Analysis of People LabAalborg UniversityDenmark

Personalised recommendations