cvpr cvpr2013 cvpr2013-386 cvpr2013-386-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: unkown-author
Abstract: We address the problem of long-term object tracking, where the object may become occluded or leave-the-view. In this setting, we show that an accurate appearance model is considerably more effective than a strong motion model. We develop simple but effective algorithms that alternate between tracking and learning a good appearance model given a track. We show that it is crucial to learn from the “right” frames, and use the formalism of self-paced curriculum learning to automatically select such frames. We leverage techniques from object detection for learning accurate appearance-based templates, demonstrating the importance of using a large negative training set (typically not used for tracking). We describe both an offline algorithm (that processes frames in batch) and a linear-time online (i.e. causal) algorithm that approaches real-time performance. Our models significantly outperform prior art, reducing the average error on benchmark videos by a factor of 4.
[1] L. Matthews, T. Ishikawa, and S. Baker, “The template update problem,” IEEE PAMI, 2004. 1
[2] Y. Bengio, J. Louradour, R. Collobert, and J. Weston, “Curriculum learning,” in ICML, pp. 41–48, ACM, 2009. 1
[3] M. Kumar, B. Packer, and D. Koller, “Self-paced learning for latent variable models,” NIPS, 2010. 1, 3
[4] R. Fan, K. Chang, C. Hsieh, X. Wang, and C. Lin, “Liblinear: A library for large linear classification,” JMLR, vol. 9, pp. 1871–1874, 2008. 1, 3, 4, 5
[5] V. Vapnik, The nature of statistical learning theory. springer, 1999. 2, 3
[6] Z. Kalal, K. Mikolajczyk, and J. Matas, “Tracking-LearningDetection,” IEEE PAMI, 2011. 2, 4, 5, 7
[7] B. Babenko, M. Yang, and S. Belongie, “Robust object tracking with online multiple instance learning,” IEEE PAMI, vol. 33, no. 8, pp. 1619–1632, 2011. 2, 5, 7
[8] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in CVPR, IEEE, 2005. 2, 6
[9] A. Yilmaz, O. Javed, and M. Shah, “Object tracking: A survey,” Acm Computing Surveys (CSUR), vol. 38, no. 4, p. 13, 2006. 2
[10] D. Comaniciu, V. Ramesh, and P. Meer, “Kernel-based object tracking,” IEEE PAMI, vol. 25, no. 5, 2003. 2
[11] A. Jepson, D. Fleet, and T. El-Maraghi, “Robust online appearance models for visual tracking,” IEEE PAMI, vol. 25, no. 10, pp. 1296–131 1, 2003. 2
[12] D. Ross, J. Lim, R. Lin, and M. Yang, “Incremental learning for robust visual tracking,” IJCV, vol. 77, no. 1, 2008. 2
[13] K. Lee, J. Ho, M. Yang, and D. Kriegman, “Visual tracking and recognition using probabilistic appearance manifolds,” CVIU, vol. 99, no. 3, pp. 303–33 1, 2005. 2
[14] X. Mei and H. Ling, “Robust visual tracking and vehicle classification via sparse representation,” IEEE PAMI, vol. 33, no. 11, pp. 2259–2272, 2011. 2
[15] B. Liu, J. Huang, L. Yang, and C. Kulikowsk, “Robust tracking using local sparse appearance model and k-selection,” in CVPR, IEEE, 2011. 2
[16] R. Collins, Y. Liu, and M. Leordeanu, “Online selection of discriminative tracking features,” IEEE PAMI, vol. 27, no. 10, pp. 1631–1643, 2005. 2
[17] H. Grabner, C. Leistner, and H. Bischof, “Semi-supervised on-line boosting for robust tracking,” ECCV, pp. 234–247, 2008. 2
[18] S. Avidan, “Ensemble tracking,” IEEE PAMI, vol. 29, no. 2, pp. 261–271, 2007. 2
[19] S. Avidan, “Support vector tracking,” IEEE PAMI, vol. 26, no. 8, pp. 1064–1072, 2004. 2
[20] S. Hare, A. Saffari, and P. Torr, “Struck: Structured output tracking with kernels,” in ICCV, 2011. 2
[21] M. Isard and A. Blake, “Condensation-conditional density propagation for visual tracking,” IJCV, 1998. 2
[22] K. Okuma, A. Taleghani, N. Freitas, J. Little, and D. Lowe, “A boosted particle filter: Multitarget detection and tracking,” ECCV, pp. 28–39, 2004. 2
[23] J. Kwon and K. Lee, “Visual tracking decomposition,” in CVPR, pp. 1269–1276, IEEE, 2010. 2
[24] D. Park, J. Kwon, and K. Lee, “Robust visual tracking using autoregressive hidden markov model,” in CVPR, pp. 1964– 1971, IEEE, 2012. 2, 5, 7
[25] Y. Bai and M. Tang, “Robust tracking via weakly supervised ranking svm,” in CVPR, pp. 1854–1861, IEEE, 2012. 2, 7
[26] Y. Wu and T. Huang, “Color tracking by transductive learning,” in CVPR, vol. 1, pp. 133–138, IEEE, 2000. 2
[27] Y. Zha, Y. Yang, and D. Bi, “Graph-based transductive learn-
[28]
[29]
[30] [3 1]
[32]
[33] ing for robust visual tracking,” Pattern Recognition, vol. 43, no. 1, pp. 187–196, 2010. 2 A. Buchanan and A. Fitzgibbon, “Interactive feature tracking using kd trees and dynamic programming,” in CVPR, vol. 1, pp. 626–633, IEEE, 2006. 3 Z. Kalal, K. Mikolajczyk, and J. Matas, “Forward-Backward Error: Automatic Detection of Tracking Failures,” ICPR, 2010. 7 A. Adam, E. Rivlin, and I. Shimshoni, “Robust fragmentsbased tracking using the integral histogram,” in CVPR, vol. 1, pp. 798–805, IEEE, 2006. 7 J. Santner, C. Leistner, A. Saffari, T. Pock, and H. Bischof, “Prost: Parallel robust online simple tracking,” in CVPR, pp. 723–730, IEEE, 2010. 7 S. Gu, Y. Zheng, and C. Tomasi, “Efficient visual object tracking with online nearest neighbor classifier,” ACCV, pp. 271–282, 2011. 7 H. Grabner, M. Grabner, and H. Bischof, “Real-time tracking via on-line boosting,” in Proc. BMVC, vol. 1, 2006. 7 222333888644