Advertisement

Robust multiple car tracking with occlusion reasoning

  • Dieter Koller
  • Joseph Weber
  • Jitendra Malik
Motion Segmentation and Tracking
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)

Abstract

We address the problem of occlusion in tracking multiple 3D objects in a known environment. For that purpose we employ a contour tracker based on intensity and motion boundaries. The motion of a contour enclosing the image of a vehicle is assumed to be well describable by an affine motion model with a translation and a change in scale. Contours are represented by closed cubic splines the position and motion of which are estimated along the image sequence. In order to employ linear Kalman Filters we decompose the estimation process in two filters: one for estimating the affine motion parameters and one for estimating the shape of the contours of the vehicles. Occlusion detection is performed by intersecting the depth ordered regions associated to the objects. The intersection part is then excluded in the motion and shape estimation. Occlusion reasoning also improves the shape estimation in case of adjacent objects where shape estimates can be corrupted by image data of other objects. In this way we obtain robust motion estimates and trajectories for vehicles even in the case of occlusions, as we show in some experiments with real world traffic scenes.

Keywords

Convex Polygon Partial Occlusion Active Contour Model Shape Estimation Motion Coherence 
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.

References

  1. [Bartels et al. 87]
    R. Bartels, J. Beatty, B. Barsky, An Introduction to Splines for use in Computer Vision, Morgan Kaufmann, 1987.Google Scholar
  2. [Blake et al. 93]
    A. Blake, R. Curwen, A. Zisserman, Affine-invariant contour tracking with automatic control of spatiotemporal scale, in Proc. Int. Conf. on Computer Vision, Berlin, Germany, May. 11–14, 1993, pp. 66–75.Google Scholar
  3. [Cipolla & Blake 92]
    R. Cipolla, A. Blake, Surface Orientation and Time to Contact from Image Divergence and Deformation, in Proc. Second European Conference on Computer Vision, S. Margherita, Ligure, Italy, May 18–23, 1992, G. Sandini (ed.), Lecture Notes in Computer Science 588, Springer-Verlag, Berlin, Heidelberg, New York, 1992, pp. 187–202.Google Scholar
  4. [Curwen & Blake 92]
    R. Curwen, A. Blake, Active Vision, MIT Press, Cambridge, MA, 1992, chapter Dynamic Contours: Real-time Active Snakes, pp. 39–57.Google Scholar
  5. [Gelb 74]
    A. Gelb (ed.), Applied Optimal Estimation, The MIT Press, Cambridge, MA and London, UK, 1974.Google Scholar
  6. [Huang et al. 93]
    T. Huang, G. Ogasawara, S. Russell, Symbolic Traffic Scene Analysis Using Dynamic Belief Networks, in AAAI Workshop on AI in IVHS, Washington D.C., 1993.Google Scholar
  7. [Karmann & von Brandt 90]
    Klaus-Peter Karmann, Achim von Brandt, Moving Object Recognition Using an Adaptive Background Memory, in V Cappellini (ed.), Time-Varying Image Processing and Moving Object Recognition, 2, Elsevier, Amsterdam, The Netherlands, 1990.Google Scholar
  8. [Kass et al. 88]
    M. Kass, A. Witkin, D. Terzopoulos, Snakes: Active Contour Models, International Journal of Computer Vision 1 (1988) 321–331.Google Scholar
  9. [Kilger 92]
    Michael Kilger, A Shadow Handler in a Video-based Real-time Traffic Monitoring System, in IEEE Workshop on Applications of Computer Vision, Palm Springs, CA, 1992, pp. 1060–1066.Google Scholar
  10. [Koenderink 86]
    J.J. Koenderink, Optic flow, Visual Research 26 (1986) 161–180.Google Scholar
  11. [Koller et al. 91]
    D. Koller, N. Heinze, H.-H. Nagel, Algorithmic Characterization of Vehicle Trajectories from Image Sequences by Motion Verbs, in IEEE Conf. Computer Vision and Pattern Recognition, Lahaina, Maui, Hawaii, June 3–6, 1991, pp. 90–95.Google Scholar
  12. [Koller et al. 93]
    D. Koller, J. Weber, J. Malik, Robust Multiple Car Tracking with Occlusion Reasoning, technical report UCB/CSD-93-780, University of California at Berkeley, Oktober 1993.Google Scholar
  13. [Létang et al. 93]
    J.M. Létang, V. Rebuffel, P. Bouthemy, Motion detection robust to pertubations: a statistical regularization and temporal integration framework, in Proc. Int. Conf. on Computer Vision, Berlin, Germany, May. 11–14, 1993, pp. 21–30.Google Scholar
  14. [Meyer & Bouthemy 93]
    F. Meyer, P. Bouthemy, Exploiting the Temporal Coherence of Motion for Linking Partial Spatiotemporal Trajectories, in IEEE Conf. Computer Vision and Pattern Recognition, New York City, NY, June 15–17, 1993, pp. 746–747.Google Scholar
  15. [Murray et al. 93]
    D.W. Murray, P.F. McLauchlan, I.D. Reid, P.M. Sharkey, Reactions to Peripheral Image Motion using a Head/Eye Platform, in Proc. Int. Conf. on Computer Vision, Berlin, Germany, May. 11–14, 1993, pp. 403–411.Google Scholar
  16. [Rao 92]
    B.S.Y. Rao, Active Vision, MIT Press, Cambridge, MA, 1992, chapter Data Association Methods for Tracking Systems, pp. 91–105.Google Scholar
  17. [Terzopoulos & Szeliski 92]
    D. Terzopoulos, R. Szeliski, Active Vision, MIT Press, Cambridge, MA, 1992, chapter Tracking with Kalman Snakes, pp. 3–20.Google Scholar
  18. [Zheng & Chellappa 93]
    Q. Zheng, R. Chellappa, Automatic Feature Point Extraction and Tracking in Image Sequences for Unknown Camera Motion, in Proc. Int. Conf. on Computer Vision, Berlin, Germany, May. 11–14, 1993, pp. 335–339.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Dieter Koller
    • 1
  • Joseph Weber
    • 1
  • Jitendra Malik
    • 1
  1. 1.EECS Dept.University of California at BerkeleyBerkeleyUSA

Personalised recommendations