Abstract
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.
Chapter PDF
Similar content being viewed by others
Keywords
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
Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Comput. Surv. (2006)
Black, M.J., Jepson, A.D.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. IJCV 26, 63–84 (1998)
Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. In: CVPR (2001)
Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: ECCV, pp. 343–356 (1996)
Lim, J., Ross, D., Lin, R., Yang, M.: Incremental learning for visual tracking. In: NIPS, pp. 793–800 (2004)
Lee, K.C., Kriegman, D.: Online learning of probabilistic appearance manifolds for video-based recognition and tracking. In: CVPR, pp. 852–859 (2005)
Elgammal, A.: Learning to track: Conceptual manifold map for closed-form tracking. In: CVPR, pp. 724–730 (2005)
Avidan, S.: Support vector tracking. PAMI (2004)
Avidan, S.: Ensemble tracking. In: CVPR, vol. 2, pp. 494–501 (2005)
Collins, R.T., Liu, Y., Leordeanu, M.: Online selection of discriminative tracking features. In: PAMI, vol. 27, pp. 1631–1643 (2005)
Nguyen, H.T., Smeulders, A.W.: Robust tracking using foreground-background texture discrimination. IJCV 2006 (2006)
Oza, N.C., Russell, S.: Online bagging and boosting. In: International Workshop on Artificial Intelligence and Statistics (2001)
Grabner, M., Grabner, H., Bischof, H.: Learning features for tracking. In: CVPR (2007)
Liu, X., Yu, T.: Gradient feature selection for online boosting. In: ICCV (2007)
Lasserre, J.A., Bishop, C.M., Minka, T.P.: Principled hybrids of generative and discriminative models. In: CVPR (2006)
Ng, A.Y., Jordan, M.I.: On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes. In: NIPS (2001)
Raina, R., Shen, Y., Ng, A.Y., McCallum, A.: Classification with hybrid generative/discriminative models. In: NIPS (2003)
Lin, R.S., Ross, D., Lim, J., Yang, M.H.: Adaptive discriminative generative model and its applications. In: NIPS (2004)
Yang, M., Wu, Y.: Tracking non-stationary appearances and dynamic feature selection. In: CVPR (2005)
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT (1998)
Levin, A., Viola, P., Freund, Y.: Unsupervised improvement of visual detectors using co-training. In: ICCV (2003)
Javed, O., Ali, S., Shah, M.: Online detection and classification of moving objects using progressively improving detectors. In: CVPR (2005)
Tang, F., Brennan, S., Zhao, Q., Tao, H.: Co-tracking using semi-supervised support vector machines. In: ICCV (2007)
Bordes, A., Ertekin, S., Weston, J., Bottou, L.: Fast kernel classifiers with online and active learning. In: JMLR 2005, pp. 1579–1619 (2005)
Cauwenberghs, G., Poggio, T.: Incremental and decremental support vector machine learning. In: NIPS (2001)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)
Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. IJCV, 5–28 (1998)
Moghaddam, B., Pentland, A.: Probabilistic visual learning for object representation. PAMI 19, 696–710 (1997)
Hall, P., Marshall, D., Martin, R.: Merging and splitting eigenspace models. In: IEEE PAMI, pp. 1042–1049 (2000)
Bjoerck, A., Golub, G.H.: Numerical methods for computing angles between linear subspaces. Mathematics of computation, 579–594 (1973)
Vapnik, V.N.: Statistical Learning Theory. John Wiley Sons, Chichester (1998)
Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers (1999)
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)
Kim, M., Kumar, S., Pavlovic, V., Rowley, H.: Face Tracking and Recognition with Visual Constraints in Real-World Videos. In: IEEE CVPR (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Electronic Supplementary Material
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yu, Q., Dinh, T.B., Medioni, G. (2008). Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88688-4_50
Download citation
DOI: https://doi.org/10.1007/978-3-540-88688-4_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88685-3
Online ISBN: 978-3-540-88688-4
eBook Packages: Computer ScienceComputer Science (R0)