Advertisement

A Novel Spatio-temporal Approach to Handle Occlusions in Vehicle Tracking

  • Alessandro Bevilacqua
  • Stefano Vaccari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4141)

Abstract

In Intelligent Transportation Systems (ITS’s), the process of vehicle tracking is often needed to permit higher-level analysis. However, during occlusions features could “jump” from an object to another one, thus resulting in tracking errors. Our method exploits second order statistics to assess the correct membership of features to respective objects, thus reducing false alarms due to splitting. As a consequence, object’s properties like area and centroid can be extracted stemming from feature points with a higher precision. We firstly validated our method on toy sequences built ad hoc to produce strong occlusions artificially and subsequently on sequences taken from a traffic monitoring system. The experimental results we present prove the effectiveness of our approach even in the presence of strong occlusions. At present, the algorithm is working in the daytime in the Traffic Monitoring System of the city where we have been living.

Keywords

False Alarm Tracking Error Tracking Algorithm Vehicle Tracking Monocular Camera 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Beymer, D., McLauchlan, P., Coifman, B., Malik, J.: A Real-Time Computer Vision System for Measuring Traffic Parameters. In: Proc. IEEE CVPR, San Juan, Puerto Rico, pp. 495–501 (1997)Google Scholar
  2. 2.
    Sugaya, Y., Kanatani, K.: Outlier Removal for Motion Tracking by Subspace Separation. In: 8th Symposium on Sensing via Image Information (SSII 2002), Yokohama, Japan, pp. 603–608 (July 2002)Google Scholar
  3. 3.
    Nguyen, H.T., Smeulders, A.W.M.: Fast Occluded Object Tracking by a Robust Appearance Filter. IEEE Transactions on PAMI, 1099–1104 (August 2004)Google Scholar
  4. 4.
    Weiss, Y.: Segmentation using eigenvectors: a unifying view. In: Proc. IEEE ICCV, pp. 975–982 (1999)Google Scholar
  5. 5.
    Bevilacqua, A., Di Stefano, L., Vaccari, S.: Occlusion Robust Vehicle Tracking based on SOM (Self-Organizing Map). In: 7th IEEE Workshop on Motion and Video Computing (Motion 2005), Breckenridge, CO, USA, October 5-7, pp. 84–89 (2005)Google Scholar
  6. 6.
    Bevilacqua, A., Di Stefano, L., Lanza, A.: An efficient motion detection algorithm based on a statistical non parametric noise model. In: 17th IEEE International Conference on Image Processing (ICIP 2004), Singapore, October 24-27, pp. 2347–2350 (2004)Google Scholar
  7. 7.
    Bevilacqua, A., Di Stefano, L., Lanza, A.: A Simple Self-Calibration Method To Infer A Non-Parametric Model Of The Imaging System Noise. In: 7th IEEE Workshop on Motion and Video Computing (Motion 2005), Breckenridge, CO, USA, January 5-7, vol. 2, pp. 229–234 (2005)Google Scholar
  8. 8.
    Xiao, J., Shah, M.: Motion Layer Extraction in the Presence of Occlusion Using Graph Cut. In: Proc. IEEE CVPR, Washington, DC, USA, vol. 2, pp. 972–979 (2004)Google Scholar
  9. 9.
    Shi, J., Tomasi, C.: Good features to track. In: Proc. IEEE CVPR, pp. 593–600 (1994)Google Scholar
  10. 10.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: DARPA Image Understanding Workshop, pp. 121–130 (1981)Google Scholar
  11. 11.
    Birchfield, S.: Derivation of Kanade-Lucas-Tomasi tracking equation (unpublished, January 1997)Google Scholar
  12. 12.
    Baker, S., Matthews, I.: Lucas-Kanade 20 Years On: A Unifying Framework. IJCV 56(3), 221–255 (2004)CrossRefGoogle Scholar
  13. 13.
    Chang, P., Krumm, J.: Object Recognition with Color Cooccurrence Histograms. In: Proc. IEEE CVPR, Fort Collins, CO, pp. 498–504 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Alessandro Bevilacqua
    • 1
  • Stefano Vaccari
    • 1
  1. 1.DEIS – ARCES (Advanced Research Center on Electronic Systems)University of BolognaBolognaItaly

Personalised recommendations