Author : Sandeep G.S 1
Date of Publication :7th January 2015
Abstract: The key idea of Adaptive tracking is how to train an online discriminative classifier which can well separate object from its local background. The classifier is incrementally updated using positive and negative samples extracted from the current frame around the detected object location. If the detection is less accurate thereby leading to visual drift. Recently, the multiple instances learning (MIL) based tracker has been proposed to solve these problems to some degree. It puts samples into the positive and negative bags, and then selects some features with an online boosting method via maximizing the bag likelihood function. Finally, the selected features are combined for classification. In MIL tracker, the features are selected by a likelihood function, which can be less informative to tell the target from complex background. Motivated by the active learning method, in this paper we propose an enhanced active feature selection approach which is able to select more informative features than MIL tracker by using the Fisher information criterion to measure the uncertainty of classification model. More specifically, we propose an online boosting feature selection approach via optimizing the Fisher information criterion, which can yield more robust and efficient real-time object tracking performance. Experimental evaluations on challenging sequences demonstrate the efficiency, accuracy and robustness of the proposed tracker in comparison with state-of-the-arts.
- A. Yilmaz, O. Javed, and M. Shah, “Object tracking: a survey,” ACM Comput. Sur., vol. 38, no. 4, Dec. 2006.
- B. Babenko, M.-H. Yang, and S. Belongie, “Robust Object Tracking with Online Multiple Instance Learning,” IEEE Trans. Pattern Anal. Mach Intell., vol. 33, no. 8, pp. 1619–1632, 2011.
- Burr Settles, “Active learning literature survey,” Technical Report 1648, University of Wisconsin Madison, 2009.
- . M. Black, A. Jepson, and Eigentracking, “Robust matching and tracking of articulated objects using a viewbased representation,” in Proc. Eur. Conf Comput. Vision., 1996, pp. 329–342.
- A. Jepson, D. Fleet, and T. Maraghi, “Robust online appearance models for visual tracking,” IEEE Trans. Pattern. Anal. Mach. Intell., vol. 25, no. 10, pp. 1296–1311, 2003.
- J. Ho, K. Lee, M. Yang, and D. Kriegman, “Visual tracking using learned linear subspace,” in Proc.IEEE Conf. Comput. Vis. Pattern Recog., 2004, pp. 782–789.
- D. Ross, J. Lim, R. Lin, and M. Yang, “Incremental learning for robust visual tracking,” Int. J.Comput. Vis., vol. 77, no. 1, pp. 125–141, 2008.
- A. Adam, E. Rivlin and I. Shimshoni, “Robust fragments-based tracking using the integral histogram,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2006, pp. 798–805
- X. Mei and H. Ling, “Robust visual tracking using l1 minimization,” in Proc. IEEE Conf. Comput. Vision., 2009, pp. 1436–1443.
- J. Kwon and K. Lee, “Visual tracking decomposition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2010, pp. 1269–1276.
- L. Sun and G. Liu, “Visual object tracking based on combination of local description and global representation,” IEEE Trans. Circuits Syst. Video Technol., vol. 21, no. 4, pp. 408–420, 2011
- D. Comaniciu, V. Ramesh, and P. Meer, “Kernelbased object tracking,” IEEE Trans. Pattern Anal.Mach. Intell., vol. 25, no. 5, pp. 564–575, 2003.
- S. Avidan, “Support vector tracking,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 26, no. 8, pp.1064–1072, 2004
- S. Avidan, “Ensemble tracking,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no.2, pp. 261–271,2007
- R. Collins, Y. Liu, and M. Leordeanu, “Online selection of discriminative tracking features,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 10, pp. 1631–1643, 2005.
- J. Zhu, Y. Lao, and Y. Zheng, “Object tracking in structured environments for video surveillance applications,” IEEE Trans. Circuits Syst. Video Technol., vol. 20, no. 2, pp. 223–235, 2010.
- H. Grabner, M. Grabner, and H. Bischof, “Real-time tracking via online boosting,” in British Machine Vision Conference, 2006, pp. 47–56.
- H. Grabner, C. Leistner, and H. Bischof, “Semisupervised on-line boosting for robust tracking,” in Proc. Eur. Conf. Comput. Vision., 2008, pp. 234–247.
- Z. Kalal, J. Matas, and K. Mikolajczyk, “P-N learning: bootstrapping binary classifiers by structural constraints,” in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2010, pp. 49–56.
- K. Zhang, L. Zhang, and M.-H. Yang, “Real-time compressive tracking,” In Proc. Eur. Conf. Comput.Vis., 2012.
- E. Candes and T. Tao, “Near optimal signal recovery from random projections and universal encoding strategies.,” IEEE Trans. Inform. Theory, vol. 52, no. 12, pp. 5406–5425, 2006.
- T. Dietterich, R. Lathrop, and T. Perez, “Solving the multiple instance problem with axis-parallel rectangles,” Artificial Intelligence, pp. 31–71, 1997.
- P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc.IEEE Conf. Comput. Vis. Pattern Recog., 2001, pp. 511–518.
- M. Cover and J. Thomas, elements of information theory, New York: Wiley, 1991.
- T. Zhang and F. Oles, “A probability analysis on the value of unlabeled data for classification problems,” in Pro. Int. Conf. on Machine Learning., 2000, pp. 1191–1198
- B. Settles, M. Craven, and S. Ray, “Multiple-instance active learning,” In Proc. Adv. Neural Inf.Process. Syst., 2008, pp. 1289–1296.
- D. Zhang, F. Wang, Z. Shi, and C. Zhang, “Interaction localized content based image retrieval with multipleinstance active learning,” Pattern Recognit., vol. 43, pp. 478–484, 2010.