Projective Kalman Filter: Multiocular Tracking of 3D Locations Towards Scene Understanding

  • C. Canton-Ferrer
  • J. R. Casas
  • A. M. Tekalp
  • M. Pardàs
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3869)


This paper presents a novel approach to the problem of estimating and tracking 3D locations of multiple targets in a scene using measurements gathered from multiple calibrated cameras. Estimation and tracking is jointly achieved by a newly conceived computational process, the Projective Kalman filter (PKF), allowing the problem to be treated in a single, unified framework. The projective nature of observed data and information redundancy among views is exploited by PKF in order to overcome occlusions and spatial ambiguity. To demonstrate the effectiveness of the proposed algorithm, the authors present tracking results of people in a SmartRoom scenario and compare these results with existing methods as well.


Kalman Filter Projective Nature Projective Geometry Data Association Foreground Region 
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.
    Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. on Signal Proc. 50(2), 174–188 (2002)CrossRefGoogle Scholar
  2. 2.
    Bar-Shalom, J., Fortmann, T.E.: Tracking and Data Association. Academic Press, London (1988)zbMATHGoogle Scholar
  3. 3.
    Black, J., Ellis, T.: Multi Camera Image Tracking. In: Proc. Work. on Motion and Video Computing (2001)Google Scholar
  4. 4.
    Canton-Ferrer, C., Casas, J.R., Pard‘as, M.: Towards a bayesian approach to robust finding correspondences in multiple view geometry environments. In: Sunderam, V.S., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2005. LNCS, vol. 3515, pp. 281–289. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Chang, T.H., Gong, S.: Tracking Multiple People with a Multi-Camera System. In: Proc. IEEE Work. on Multi-Object Tracking (2001)Google Scholar
  6. 6.
    Darrell, T., Gordon, G., Harville, M.: Integrated person tracking using stereo, color and pattern detection. Int. J. of Computer Vision 37(2), 175–185 (2000)CrossRefzbMATHGoogle Scholar
  7. 7.
    Dockstader, S.L., Tekalp, A.M.: Multiple camera tracking of interacting and occluded human motion. Proc. of IEEE 89(10), 1441–1455 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Dockstader, S.L., Berg, M.J., Tekalp, A.M.: Stochastic Kinematic Modeling and Feature Extraction for Gait Analysis. IEEE Trans. on Imag. Proc. 12(8), 962–976 (2003)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Focken, D., Stiefelhagen, R.: Towards vision-based 3D people tracking in a smart room. In: Proc. IEEE Int. Conf. on Multimodal Interfaces, pp. 400–405 (2002)Google Scholar
  10. 10.
    Garcia, O.: Mapping 2D images and 3D world objects in a multicamera system. Ms. Thesis. Technical University of Catalonia (2004)Google Scholar
  11. 11.
    Haritaoglu, I., Harwood, D., David, L.: W4: Who?When?Where?What?A real time system for detecting and tracking people. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 877–892. Springer, Heidelberg (1998)Google Scholar
  12. 12.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)CrossRefzbMATHGoogle Scholar
  13. 13.
    Julier, S.J., Uhlmann, J.K.: A New Extension of the Kalman Filter to Nonliner Systems. In: Proc. of AeroSense: The 11th Int.Symp. on Aerospace/Defence Sensing, Simulation and Controls (1997)Google Scholar
  14. 14.
    Jung, S.K., Wohn, K.Y.: 3D Tracking and Motion Estimation using Hierarchical Kalman Filter. Proc. IEE Visual Image Signal Process. 144(5) (1997)Google Scholar
  15. 15.
    Kalman, R.E.: A New Approach to Linear Filtering and Prediction Problems. Trans. of the ASME–J. of Basic Engineering 82-D, 35–45 (1960)CrossRefGoogle Scholar
  16. 16.
    Lewis, F.L.: Optimal Estimation. John Wiley and Sons, New York (1986)Google Scholar
  17. 17.
    Mikic, I., Santini, S., Jain, R.: Tracking Objects in 3D using Multiple Camera Views. In: Proc. Asian Conf. on Computer Vision, pp. 234–239 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • C. Canton-Ferrer
    • 1
  • J. R. Casas
    • 1
  • A. M. Tekalp
    • 2
  • M. Pardàs
    • 1
  1. 1.Technical University of CataloniaBarcelonaSpain
  2. 2.Koc UniversityIstanbulTurkey

Personalised recommendations