Bayesian Loop for Synergistic Change Detection and Tracking

  • Samuele Salti
  • Alessandro Lanza
  • Luigi Di Stefano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6468)


In this paper we investigate Bayesian visual tracking based on change detection. Although in many proposals change detection is key for tracking, little attention has been paid to sound modeling of the interaction between the change detector and the tracker. In this work, we develop a principled framework whereby both processes can virtuously influence each other according to a Bayesian loop: change detection provides a completely specified observation likelihood to the tracker and the tracker provides an informative prior to the change detector.


Kalman Filter Change Detection Visual Tracking Soccer Video Observation Likelihood 
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.
    Maskell, S., Gordon, N.: A tutorial on particle filters for on-line nonlinear/non-gaussian bayesian tracking. IEEE Trans. on Signal Processing 50, 174–188 (2001)Google Scholar
  2. 2.
    Lanza, A., Di Stefano, L., Soffritti, L.: Bayesian order-consistency testing with class priors derivation for robust change detection. In: AVSS, pp. 460–465 (2009)Google Scholar
  3. 3.
    Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Gool, L.V.: Depth-from-recognition: Inferring metadata by cognitive feedback. In: 3DRR (2007)Google Scholar
  4. 4.
    Haritaoglu, I., Harwood, D., Davis, L.S.: W4: Real-time surveillance of people and their activities. IEEE T-PAMI 22, 809–830 (2000)CrossRefGoogle Scholar
  5. 5.
    Stauffer, C., Grimson, W.: Adaptive background mixture models for real-time tracking. In: Proc. of the CVPR 1999, pp. 246–252 (1999)Google Scholar
  6. 6.
    Harville, M., Li, D.: Fast, integrated person tracking and activity recognition with plan-view templates from a single stereo camera. In: CVPR, vol. 2, pp. 398–405 (2004)Google Scholar
  7. 7.
    Isard, M., MacCormick, J.: Bramble: A bayesian multiple-blob tracker. In: Proc. of the ICCV 2001 (2001)Google Scholar
  8. 8.
    Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. PAMI 25, 564–575 (2003)CrossRefGoogle Scholar
  9. 9.
    D’Orazio, T., Leo, M., Mosca, N., Spagnolo, P., Mazzeo, P.: A semi-automatic system for ground truth generation of soccer video sequences. In: AVSS (2009)Google Scholar
  10. 10.
    Lanza, A., Di Stefano, L.: On-line learning of background appearance changes for robust background subtraction. In: IET Int. Conf. on Imaging for Crime Detection and Prevention (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Samuele Salti
    • 1
  • Alessandro Lanza
    • 1
  • Luigi Di Stefano
    • 1
  1. 1.Computer Vision LabARCES-DEIS, University of BolognaBolognaItaly

Personalised recommendations