Dynamic Bayesian Networks for Visual Surveillance with Distributed Cameras

  • Wojciech Zajdel
  • A. Taylan Cemgil
  • Ben J. A. Kröse
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4272)


This paper presents a surveillance system for tracking multiple people through a wide area with sparsely distributed cameras. The computational core of the system is an adaptive probabilistic model for reasoning about peoples’ appearances, locations and identities. The system consists of two processing levels. At the low-level, individual persons are detected in the video frames and tracked at a single camera. At the high-level, a probabilistic framework is applied for estimation of identities and camera-to-camera trajectories of people. The system is validated in a real-world office environment with seven color cameras.


Gaussian Mixture Model Dynamic Bayesian Network Probabilistic Framework Appearance Feature Floor Plane 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lerner, U., Parr, R.: Inference in hybrid networks: Theoretical limits and practical algorithms. In: Uncertainty in Artificial Intelligence, pp. 310–318 (2001)Google Scholar
  2. 2.
    Murphy, K.: Dynamic Bayesian Networks: Representation, Inference and Learning. PhD thesis, University of California, Berkeley (2002)Google Scholar
  3. 3.
    Pasula, H., Russell, S., Ostland, M., Ritov, Y.: Tracking many objects with many sensors. In: Int. Joint Conf. on Artificial Intelligence, pp. 1160–1171 (1999)Google Scholar
  4. 4.
    Rasmussen, C.E.: The infinite Gaussian mixture model. In: Advances in Neural Information Processing Systems 12, pp. 554–560 (2000)Google Scholar
  5. 5.
    Zajdel, W.: Bayesian Visual Surveillance. From object detection to distributed cameras. PhD thesis, University of Amsterdam (2006)Google Scholar
  6. 6.
    Zajdel, W., Vlassis, N., Kröse, B.J.A.: Bayesian methods for tracking and localization. In: Aarts, E., Korts, J., Verhaegh, W. (eds.) Intelligent Algorithms, pp. 243–258. Kluwer Academic Publishers, Dordrecht (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Wojciech Zajdel
    • 1
  • A. Taylan Cemgil
    • 2
  • Ben J. A. Kröse
    • 1
  1. 1.Informatics InstituteUniversity of AmsterdamAmsterdam
  2. 2.Signal Processing and Communications LaboratoryUniversity of Cambridge 

Personalised recommendations