Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers

  • Qian Yu
  • Thang Ba Dinh
  • Gérard Medioni
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5303)


Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the field of view and then reappear. In order to track and reacquire an unknown object with limited labeling data, we propose to learn these changes online and build a model that describes all seen appearance while tracking. To address this semi-supervised learning problem, we propose a co-training based approach to continuously label incoming data and online update a hybrid discriminative generative model. The generative model uses a number of low dimension linear subspaces to describe the appearance of the object. In order to reacquire an object, the generative model encodes all the appearance variations that have been seen. A discriminative classifier is implemented as an online support vector machine, which is trained to focus on recent appearance variations. The online co-training of this hybrid approach accounts for appearance changes and allows reacquisition of an object after total occlusion. We demonstrate that under challenging situations, this method has strong reacquisition ability and robustness to distracters in background.


Unlabeled Data Discriminative Model Appearance Change Appearance Variation Generative Tracker 
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_50_MOESM1_ESM.wmv (27.4 mb)
Supplementary material (28,019 KB)


  1. 1.
    Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Comput. Surv. (2006)Google Scholar
  2. 2.
    Black, M.J., Jepson, A.D.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. IJCV 26, 63–84 (1998)CrossRefGoogle Scholar
  3. 3.
    Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. In: CVPR (2001)Google Scholar
  4. 4.
    Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: ECCV, pp. 343–356 (1996)Google Scholar
  5. 5.
    Lim, J., Ross, D., Lin, R., Yang, M.: Incremental learning for visual tracking. In: NIPS, pp. 793–800 (2004)Google Scholar
  6. 6.
    Lee, K.C., Kriegman, D.: Online learning of probabilistic appearance manifolds for video-based recognition and tracking. In: CVPR, pp. 852–859 (2005)Google Scholar
  7. 7.
    Elgammal, A.: Learning to track: Conceptual manifold map for closed-form tracking. In: CVPR, pp. 724–730 (2005)Google Scholar
  8. 8.
    Avidan, S.: Support vector tracking. PAMI (2004)Google Scholar
  9. 9.
    Avidan, S.: Ensemble tracking. In: CVPR, vol. 2, pp. 494–501 (2005)Google Scholar
  10. 10.
    Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. In: PAMI, vol. 27, pp. 1631–1643 (2005)Google Scholar
  11. 11.
    Nguyen, H.T., Smeulders, A.W.: Robust tracking using foreground-background texture discrimination. IJCV 2006 (2006)Google Scholar
  12. 12.
    Oza, N.C., Russell, S.: Online bagging and boosting. In: International Workshop on Artificial Intelligence and Statistics (2001)Google Scholar
  13. 13.
    Grabner, M., Grabner, H., Bischof, H.: Learning features for tracking. In: CVPR (2007)Google Scholar
  14. 14.
    Liu, X., Yu, T.: Gradient feature selection for online boosting. In: ICCV (2007)Google Scholar
  15. 15.
    Lasserre, J.A., Bishop, C.M., Minka, T.P.: Principled hybrids of generative and discriminative models. In: CVPR (2006)Google Scholar
  16. 16.
    Ng, A.Y., Jordan, M.I.: On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes. In: NIPS (2001)Google Scholar
  17. 17.
    Raina, R., Shen, Y., Ng, A.Y., McCallum, A.: Classification with hybrid generative/discriminative models. In: NIPS (2003)Google Scholar
  18. 18.
    Lin, R.S., Ross, D., Lim, J., Yang, M.H.: Adaptive discriminative generative model and its applications. In: NIPS (2004)Google Scholar
  19. 19.
    Yang, M., Wu, Y.: Tracking non-stationary appearances and dynamic feature selection. In: CVPR (2005)Google Scholar
  20. 20.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT (1998)Google Scholar
  21. 21.
    Levin, A., Viola, P., Freund, Y.: Unsupervised improvement of visual detectors using co-training. In: ICCV (2003)Google Scholar
  22. 22.
    Javed, O., Ali, S., Shah, M.: Online detection and classification of moving objects using progressively improving detectors. In: CVPR (2005)Google Scholar
  23. 23.
    Tang, F., Brennan, S., Zhao, Q., Tao, H.: Co-tracking using semi-supervised support vector machines. In: ICCV (2007)Google Scholar
  24. 24.
    Bordes, A., Ertekin, S., Weston, J., Bottou, L.: Fast kernel classifiers with online and active learning. In: JMLR 2005, pp. 1579–1619 (2005)Google Scholar
  25. 25.
    Cauwenberghs, G., Poggio, T.: Incremental and decremental support vector machine learning. In: NIPS (2001)Google Scholar
  26. 26.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  27. 27.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. IJCV, 5–28 (1998)Google Scholar
  28. 28.
    Moghaddam, B., Pentland, A.: Probabilistic visual learning for object representation. PAMI 19, 696–710 (1997)CrossRefGoogle Scholar
  29. 29.
    Hall, P., Marshall, D., Martin, R.: Merging and splitting eigenspace models. In: IEEE PAMI, pp. 1042–1049 (2000)Google Scholar
  30. 30.
    Bjoerck, A., Golub, G.H.: Numerical methods for computing angles between linear subspaces. Mathematics of computation, 579–594 (1973)Google Scholar
  31. 31.
    Vapnik, V.N.: Statistical Learning Theory. John Wiley Sons, Chichester (1998)MATHGoogle Scholar
  32. 32.
    Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers (1999)Google Scholar
  33. 33.
    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: IEEE CVPR (2007)Google Scholar
  34. 34.
    Kim, M., Kumar, S., Pavlovic, V., Rowley, H.: Face Tracking and Recognition with Visual Constraints in Real-World Videos. In: IEEE CVPR (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Qian Yu
    • 1
  • Thang Ba Dinh
    • 1
  • Gérard Medioni
    • 1
  1. 1.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations