Abstract
Tracking objects of interest in video sequences, referred in computer vision literature as video tracking or visual tracking, is an essential task for intelligent machines able to understand and react to the surrounding environment. This work investigates the problem of robust, long-term visual tracking of unknown objects in unconstrained environments. Such problem is affected by several challenging difficulties arising from fast camera movements, partial or total object occlusions and temporal disappearance. We describe a novel framework based on Tracking-Learning-Detection (TLD), that combine bayesian optimal filtering with pn on-line learning theory [12] to adapt target visual likelihood during tracking. We designed particle filtering algorithm for parameter inference and propose a solution that enables accurate and efficient tracking. The performance and the long-term stability are demonstrated and evaluated on a set of challenging video sequences usually employed to test tracking algorithms.
Keywords
- Visual tracking
- MCMC particle filter
- Adaptive likelihood
Chapter PDF
References
Avidan, S.: Ensemble tracking. In: CVPR, pp. 494–501 (2005)
Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1619–1632 (2011)
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, COLT 1998, pp. 92–100. ACM, New York (1998)
Yves Bouguet, J.: Pyramidal implementation of the lucas kanade feature tracker. Intel Corporation, Microprocessor Research Labs (2000)
Choi, W., Savarese, S.: Multiple target tracking in world coordinate with single, minimally calibrated camera. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 553–567. Springer, Heidelberg (2010)
Tang, F., Brennan, S., Zhao, Q., Tao, H.: Co-tracking using semi-supervised support vector machines. IEEE Trans. Pattern Anal. Mach. Intell., 1–8 (August 2007)
Fan, J., Shen, X., Wu, Y.: Closed-loop adaptation for robust tracking. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 411–424. Springer, Heidelberg (2010)
Grossberg, S.: Competitive learning: From interactive activation to adaptive resonance. Cognitive Science 11(1), 23–63 (1987)
Hoey, J.: Tracking using flocks of features, with application to assisted handwashing. In: British Machine Vision Conference BMVC (2006)
Jepson, A.D., Fleet, D.J., El-maraghi, T.F.: Robust online appearance models for visual tracking, pp. 415–422 (2001)
Kalal, Z., Mikolajczyk, K., Matas, J.: Forward-backward error: Automatic detection of tracking failures. In: Proceedings of the 2010 20th International Conference on Pattern Recognition, ICPR 2010, pp. 2756–2759 (2010)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(7), 1409–1422 (2012)
Lepetit, V., Lagger, P., Fua, P.: Randomized trees for real-time keypoint recognition. In: CVPR, pp. 775–781 (2005)
Lu, L., Hager, G.D.: A nonparametric treatment for location/segmentation based visual tracking. In: 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, Minnesota, USA, June 18-23, IEEE Computer Society (2007)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence, IJCAI 1981, vol. 2, pp. 674–679. Morgan Kaufmann Publishers Inc., San Francisco (1981)
Matthews, I., Ishikawa, T., Baker, S.: The template update problem. IEEE PAMI 26, 810–815 (2003)
Ross, D.A., Lim, J., Lin, R.S., Yang, M.H.: Incremental learning for robust visual tracking (2008)
Saffari, A., Leistner, C., Santner, J., Godec, M., Bischof, H.: On-line random forests
Salti, S., Cavallaro, A., di Stefano, L.: Adaptive appearance modeling for video tracking: Survey and evaluation. IEEE TIP 21(10), 4334–4348 (2012)
Shi, J., Tomasi, C.: Good features to track. In: 1994 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 1994), pp. 593–600 (1994)
Song, X., Cui, J., Zha, H., Zhao, H.: Vision-based multiple interacting targets tracking via on-line supervised learning. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 642–655. Springer, Heidelberg (2008)
Teichman, A., Thrun, S.: Tracking-based semi-supervised learning. Int. J. Rob. Res. 31(7), 804–818 (2012)
Yang, M., Lv, F., Xu, W., Gong, Y.: Detection driven adaptive multi-cue integration for multiple human tracking. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1554–1561. IEEE (2009)
Yin, Z., Collins, R.T.: On-the-fly object modeling while tracking. In: CVPR 2007, Minneapolis, Minnesota, USA, June 18-23. IEEE Computer Society (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gemignani, G., Choi, W., Ferone, A., Petrosino, A., Savarese, S. (2013). A Bayesian Approach to Tracking Learning Detection. In: Petrosino, A. (eds) Image Analysis and Processing – ICIAP 2013. ICIAP 2013. Lecture Notes in Computer Science, vol 8156. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41181-6_81
Download citation
DOI: https://doi.org/10.1007/978-3-642-41181-6_81
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41180-9
Online ISBN: 978-3-642-41181-6
eBook Packages: Computer ScienceComputer Science (R0)
-
Published in cooperation with
http://www.iapr.org/
