iccv iccv2013 iccv2013-425 iccv2013-425-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Zhibin Hong, Xue Mei, Danil Prokhorov, Dacheng Tao
Abstract: Combining multiple observation views has proven beneficial for tracking. In this paper, we cast tracking as a novel multi-task multi-view sparse learning problem and exploit the cues from multiple views including various types of visual features, such as intensity, color, and edge, where each feature observation can be sparsely represented by a linear combination of atoms from an adaptive feature dictionary. The proposed method is integrated in a particle filter framework where every view in each particle is regarded as an individual task. We jointly consider the underlying relationship between tasks across different views and different particles, and tackle it in a unified robust multi-task formulation. In addition, to capture the frequently emerging outlier tasks, we decompose the representation matrix to two collaborative components which enable a more robust and accurate approximation. We show that theproposedformulation can be efficiently solved using the Accelerated Proximal Gradient method with a small number of closed-form updates. The presented tracker is implemented using four types of features and is tested on numerous benchmark video sequences. Both the qualitative and quantitative results demonstrate the superior performance of the proposed approach compared to several stateof-the-art trackers.
[1] B. Babenko, M.-H. Yang, and S. Belongie. Robust object tracking with online multiple instance learning. TPAMI, 33(8): 1619–1632, 2011.
[2] V. Badrinarayanan, P. Perez, F. Le Clerc, and L. Oisel. Probabilistic color and adaptive multi-feature tracking with dynamically switched priority between cues. ICCV, 1–8, 2007.
[3] X. Chen, W. Pan, J. Kwok, and J. Carbonell. Accelerated gradient method for multi-task sparse learning problem. ICDM, 746–75 1, 2009.
[4] R. T. Collins, Y. Liu, and M. Leordeanu. Online selection of discriminative tracking features. TPAMI, 27(10): 1631–1643, 2005.
[5] D. Comaniciu, V. Ramesh, and P. Meer. Kernel-based object tracking. TPAMI, 25(5):564–577, 2003.
[6] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. CVPR, 1:886–893, 2005.
[7] W. Du and J. Piater. A probabilistic approach to integrating multiple cues in visual tracking. ECCV, 225–238, 2008.
[8] M. Godec, P. M. Roth, and H. Bischof. Hough-based tracking of non-rigid objects. ICCV, 81–88, 201 1.
[9] P. Gong, J. Ye, and C. Zhang. Robust multi-task feature learning. ICDM, 895– 903, 2012.
[10] Z. Hong, X. Mei, and D. Tao. Dual-force metric learning for robust distracterresistant tracker. ECCV, 513–527, 2012.
[11] M. Isard and A. Blake. Condensation-conditional density propagation for visual tracking. IJCV, 29:5–28, 1998.
[12] A. D. Jepson, D. J. Fleet, and T. F. El-Maraghi. Robust online appearance models for visual tracking. TPAMI, 25(10): 1296–13 11, 2003.
[13] Z. Kalal, J. Matas, and K. Mikolajczyk. P-n learning: Bootstrapping binary classifiers by structural constraints. CVPR, 49–56, 2010.
[14] J. Kwon and K. M. Lee. Visual tracking decomposition. CVPR, 1269–1276, 2010.
[15] H. Li, C. Shen, and Q. Shi. Real-time visual tracking using compressive sensing. CVPR, 1305–1312, 2011.
[16] B. Liu, J. Huang, L. Yang, and C. Kulikowsk. Robust tracking using local sparse appearance model and k-selection. CVPR, 13 13–1320, 2011.
[17] J. Liu, S. Ji, and J. Ye. Multi-task feature learning via efficient ℓ2 1-norm minimization. Conf. on UAI, 339–348, 2009.
[18] W. Liu and D. Tao. Multiview hessian regularization for image annotation. TIP, 22(7):2676–2687, 2013.
[19] X. Mei and H. Ling. Robust visual tracking and vehicle classification via sparse representation. TPAMI, 33(1 1):2259–2272, 2011.
[20] X. Mei, H. Ling, Y. Wu, E. Blasch, and L. Bai. Efficient minimum error bounded particle resampling l1 tracker with occlusion detection. TIP, 22(7):2661–2675, 2013.
[21] F. Moreno-Noguer, A. Sanfeliu, and D. Samaras. Dependent multiple cue integration for robust tracking. TPAMI, 30(4):670–685, 2008.
[22] Y. Nesterov. Gradient methods for minimizing composite objective function. Center for Operations Research and Econometrics (CORE), Universit catholique de Louvain, 76, 2007.
[23] T. Ojala, M. Pietikainen, and T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. TPAMI, 24(7):971–987, 2002.
[24] S. Oron, A. Bar-Hillel, D. Levi, and S. Avidan. Locally orderless tracking. CVPR, 1940–1947, 2012.
[25] N. Quadrianto and C. H. Lampert. Learning multi-view neighborhood preserving projections. ICML, 425–432, 2011.
[26] D. Ross, J. Lim, R. Lin, and M. Yang. Incremental learning for robust visual tracking. IJCV, 77(1): 125–141, 2008.
[27] X. Tan and B. Triggs. Enhanced local texture feature sets for face recognition ,
[28]
[29]
[30]
[31]
[32]
[33]
[34]
[35] under difficult lighting conditions. TIP, 19(6): 1635–1650, 2010. O. Williams, A. Blake, and R. Cipolla. Sparse bayesian learning for efficient visual tracking. TPAMI, 27(8): 1292–1304, 2005. T. Xia, D. Tao, T. Mei, and Y. Zhang. Multiview spectral embedding. TSMC, Part B, 40(6): 1438–1446, 2010. C. Xu, D. Tao, and C. Xu. A survey on multi-view learning. CoRR, abs/1304.5634, 2013. A. Yilmaz, O. Javed, and M. Shah. Object tracking: A survey. ACM Comput.Surv., 38(4): 13–45, 2006. J. Yoon, D. Kim, and K.-J. Yoon. Visual tracking via adaptive tracker selection with multiple features. ECCV, 28–41, 2012. X.-T. Yuan and S. Yan. Visual classification with multi-task joint sparse representation. CVPR, 3493–3500, 2010. K. Zhang, L. Zhang, and M.-H. Yang. Real-time compressive tracking. ECCV, 864–877, 2012. T. Zhang, B. Ghanem, S. Liu, and N. Ahuja. Robust visual tracking via multitask sparse learning. CVPR, 2042–2049, 2012. 656