Online Multi-target Tracking by Large Margin Structured Learning

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7726)


We present an online data association algorithm for multi-object tracking using structured prediction. This problem is formulated as a bipartite matching and solved by a generalized classification, specifically, Structural Support Vector Machines (S-SVM). Our structural classifier is trained based on matching results given the similarities between all pairs of objects identified in two consecutive frames, where the similarity can be defined by various features such as appearance, location, motion, etc. With an appropriate joint feature map and loss function in the S-SVM, finding the most violated constraint in training and predicting structured labels in testing are modeled by the simple and efficient Kuhn-Munkres (Hungarian) algorithm in a bipartite graph. The proposed structural classifier can be generalized effectively for many sequences without re-training. Our algorithm also provides a method to handle entering/leaving objects, short-term occlusions, and misdetections by introducing virtual agents—additional nodes in a bipartite graph. We tested our algorithm on multiple datasets and obtained comparable results to the state-of-the-art methods with great efficiency and simplicity.


Feature Vector Bipartite Graph Local Binary Pattern Consecutive Frame Data Association 
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.
    Leibe, B., Schindler, K., Van Gool, L.: Coupled detection and trajectory estimation for multi-object tracking. In: ICCV (2007)Google Scholar
  2. 2.
    Jiang, S.H., Fels, Little, J.J.: A linear programming approach for multiple object tracking. In: CVPR (2007)Google Scholar
  3. 3.
    Andriyenko, A., Schindler, K.: Globally Optimal Multi-target Tracking on a Hexagonal Lattice. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 466–479. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  4. 4.
    Zhang, R.L., Li, Y., Nevatia: Global data association for multi-object tracking using network flows. In: CVPR (2008)Google Scholar
  5. 5.
    Pirsiavash, H., Ramanan, D., Fowlkes, C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)Google Scholar
  6. 6.
    Huang, C., Wu, B., Nevatia, R.: Robust Object Tracking by Hierarchical Association of Detection Responses. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 788–801. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Li, R.Y., Huang, C., Nevatia, R.: Learning to associate: Hybridboosted multi-target tracker for crowded scene. In: CVPR (2009)Google Scholar
  8. 8.
    Kuo, C.H., Huang, C., Nevatia, R.: Multi-target tracking by on-line learned discriminative appearance models. In: CVPR (2010)Google Scholar
  9. 9.
    Kuo, C.H., Nevatia, R.: How does person identity recognition help multi-person tracking? In: CVPR (2011)Google Scholar
  10. 10.
    Yang, B., Huang, C., Nevatia, R.: Learning affinities and dependencies for multi-target tracking using a CRF model. In: CVPR (2011)Google Scholar
  11. 11.
    Brendel, W., Amer, M., Todorovic, S.: Multiobject tracking as maximum weight independent set. In: CVPR (2011)Google Scholar
  12. 12.
    Yang, B., Nevatia, R.: An online learned CRF model for multi-target tracking. In: CVPR (2012)Google Scholar
  13. 13.
    Andriyenko, A., Schindler, K.: Multi-target tracking by continuous energy minimization. In: CVPR (2011)Google Scholar
  14. 14.
    Yang, B., Nevatia, R.: Multi-target tracking by online learning of non-linear motion patterns and robust appearance models. In: CVPR (2012)Google Scholar
  15. 15.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  16. 16.
    Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV 77, 259–289 (2008)CrossRefGoogle Scholar
  17. 17.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE PAMI 32, 1627–1645 (2010)CrossRefGoogle Scholar
  18. 18.
    Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. IJCV 75, 247–266 (2007)CrossRefGoogle Scholar
  19. 19.
    Yang, M., Lv, F., Xu, W., Gong, Y.: Detection driven adaptive multi-cue integration for multiple human tracking. In: ICCV (2009)Google Scholar
  20. 20.
    Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML (2004)Google Scholar
  21. 21.
    Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Research Logistics Quarterly 2, 83–97 (1955)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: ICCV (2009)Google Scholar
  23. 23.
    Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)Google Scholar
  24. 24.
    Ess, A., Leibe, B., Schindler, K., van Gool, L.: A mobile vision system for robust multi-person tracking. In: CVPR (2008)Google Scholar
  25. 25.
    Andriluka, M., Roth, S., Schiele, B.: Monocular 3d pose estimation and tracking by detection. In: CVPR (2010)Google Scholar
  26. 26.
    PETS: IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (2009),
  27. 27.
    Vedaldi, A.: A MATLAB wrapper of SVMstruct (2011),

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringPOSTECHKorea

Personalised recommendations