Robust Object Tracking by Hierarchical Association of Detection Responses

  • Chang Huang
  • Bo Wu
  • Ramakant Nevatia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)


We present a detection-based three-level hierarchical association approach to robustly track multiple objects in crowded environments from a single camera. At the low level, reliable tracklets (i.e. short tracks for further analysis) are generated by linking detection responses based on conservative affinity constraints. At the middle level, these tracklets are further associated to form longer tracklets based on more complex affinity measures. The association is formulated as a MAP problem and solved by the Hungarian algorithm. At the high level, entries, exits and scene occluders are estimated using the already computed tracklets, which are used to refine the final trajectories. This approach is applied to the pedestrian class and evaluated on two challenging datasets. The experimental results show a great improvement in performance compared to previous methods.


False Alarm Detection Response Middle Level Pedestrian Detector Multiple Object Tracking 
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.

Supplementary material

978-3-540-88688-4_58_MOESM1_ESM.avi (17.8 mb)
Supplementary material (18,229 KB)


  1. 1.
    Comaniciu, D., Ramesh, V., Meer, P.: The Variable Bandwidth Mean Shift and Data-Driven Scale Selection. In: ICCV (2001)Google Scholar
  2. 2.
    Tomasi, C., Kanade, T.: Detection and Tracking of Point Features. Technical Report CMU-CS-91-132, Carnegie Mellon University (1991)Google Scholar
  3. 3.
    Zhao, T., Nevatia, R.: Tracking Multiple Humans in Complex Situations. IEEE trans. on PAMI 26(9), 1208–1221 (2004)CrossRefGoogle Scholar
  4. 4.
    Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. In: CVPR (2001)Google Scholar
  5. 5.
    Zhu, Q., Avidan, S., Yeh, M.C., Cheng, K.T.: Fast Human Detection Using a Cascade of Histograms of Oriented Gradients. In: CVPR (2006)Google Scholar
  6. 6.
    Wu, B., Nevatia, R.: Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors. International Journal of Computer Vision (2007)Google Scholar
  7. 7.
    Stauffer, C.: Estimating tracking sources and sinks. In: IEEE Workshop on Event Mining in Video (2003)Google Scholar
  8. 8.
    Perera, A.G.A., Srinivas, C., Hoogs, A., Brooksby, G., Hu, W.: Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions. In: CVPR (2006)Google Scholar
  9. 9.
    Li, Y., Ai, H., Yamashita, T., Lao, S., Kawade, M.: Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans. In: CVPR (2007)Google Scholar
  10. 10.
    Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Research Logistics Quarterly 2, 83–87 (1955)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Reid, D.: An algorithm for tracking multiple targets. IEEE Trans. Automatic Control 24, 843–854 (1979)CrossRefGoogle Scholar
  12. 12.
    Fortmann, T., Shalom, Y.B., Scheffe, M.: Sonar tracking of multiple targets using joint probabilistic data association. IEEE J. Oceanic Engineering 8, 173–184 (1983)CrossRefGoogle Scholar
  13. 13.
    Leibe, B., Schindler, K., Gool, L.V.: Coupled Detection and Trajectory Estimation for Multi-Object Tracking. In: ICCV (2007)Google Scholar
  14. 14.
    Okuma, K., Taleghani, A., Freitas, N.D., Little, J.J., Lowe, D.G.: A Boosted Particle Filter: Multitarget Detection and Tracking. In: ECCV (2004)Google Scholar
  15. 15.
    Yu, Q., Medioni, G., Cohen, I.: Multiple target tracking using spatio-temporal markov chain monte carlo data association. In: CVPR (2007)Google Scholar
  16. 16.
    Singh, V.K., Wu, B., Nevatia, R.: Pedestrian Tracking by Associating Tracklets using Detection Residuals. In: WMVC (2008)Google Scholar
  17. 17.
    Kaucic, R., Perera, A.G.A., Brooksby, G., Kaufhold, J., Hoogs, A.: A Unified Framework for Tracking through Occlusions and across Sensor Gaps. In: CVPR (2005)Google Scholar
  18. 18.
  19. 19.
  20. 20.

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Chang Huang
    • 1
  • Bo Wu
    • 1
  • Ramakant Nevatia
    • 1
  1. 1.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations