cvpr cvpr2013 cvpr2013-267 cvpr2013-267-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Dong Wang, Huchuan Lu, Ming-Hsuan Yang
Abstract: In this paper, we propose a generative tracking method based on a novel robust linear regression algorithm. In contrast to existing methods, the proposed Least Soft-thresold Squares (LSS) algorithm models the error term with the Gaussian-Laplacian distribution, which can be solved efficiently. Based on maximum joint likelihood of parameters, we derive a LSS distance to measure the difference between an observation sample and the dictionary. Compared with the distance derived from ordinary least squares methods, the proposed metric is more effective in dealing with outliers. In addition, we present an update scheme to capture the appearance change of the tracked target and ensure that the model is properly updated. Experimental results on several challenging image sequences demonstrate that the proposed tracker achieves more favorable performance than the state-of-the-art methods.
[1] A. Adam, E. Rivlin, and I. Shimshoni. Robust fragments-based tracking using the integral histogram. In CVPR, pages 798–805, 2006.
[2] S. Avidan. Ensemble tracking. TPAMI, 29(2):261, 2007.
[3] A. Ayvaci, M. Raptis, and S. Soatto. Occlusion detection and motion estimation with convex optimization. In NIPS, pages 100–108, 2010.
[4] B. Babenko, M.-H. Yang, and S. Belongie. Visual tracking with online multiple instance learning. In CVPR, pages 983–990, 2009.
[5] C. Bao, Y. Wu, H. Ling, and H. Ji. Real time robust ?1 tracker using accelerated proximal gradient approach. In CVPR, pages 1830–1837, 2012.
[6] I. Barrodale and F. D. K. Roberts. An improved algorithm for discrete ?1 linear approximation. SIAM Journal on Numerical Analysis, 10(5):839–848, 1973.
[7] M. J. Black. EigenTracking : Robust Matching and Tracking of Articulated Objects Using a View-Based Representation. IJCV, 26(1):63–84, 1998.
[8] Z. Chen, J. Wang, and Y. Wu. Decomposing and regularizing sparse/non-sparse components for motion field estimation. In CVPR, pages 1776–1783, 2012.
[9] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. IJCV, 88(2):303–338, 2010.
[10] H. Grabner and H. Bischof. On-line boosting and vision. In CVPR, pages 260–267, 2006.
[11] S. Hare, A. Saffari, and P. H. S. Torr. Struck: Structured output tracking with kernels. In ICCV, pages 263–270, 2011.
[12] W. Hu, X. Li, X. Zhang, X. Shi, S. J. Maybank, and Z. Zhang. Incremental tensor subspace learning and its applications to foreground segmentation and tracking. IJCV, 91(3):303–327, 2011.
[13] X. Jia, H. Lu, and M.-H. Yang. Visual tracking via adaptive structural local sparse appearance model. In CVPR, pages 1822–1829, 2012.
[14] Z. Kalal, K. Mikolajczyk, and J. Matas. Tracking-learning-detection. TPAMI, 34(7):1409–1422, 2012. 222333777755 (a) Tracking results on sequence Oc lusion1 and Oc lusion2 with heavy oc lusion and in-plane rotation. (b) Tracking results on sequence Caviar1 and Caviar2 with partial oc lusion and scale change. (c)TrackingresultsonsequenceCaviar3andDavidOutdo rwithsever oc lusion,scalechangeandposevariation. (d) Tracking results on sequence DavidIndo r, Car4 and Singer1 with il umination variation. (e) Tracking results on sequence Car1 , Deer and Fo tbal with background clut er. (f) Tracking results on sequence Jumping, Owl and Face with abrupt motion. ????????????????????????? Figure 3. Sample tracking results on fifteen challenging image sequences. This figure demonstrates the results of the IVT [20], MIL [4], TLD [14], APGL1 [5], SCM [32], ASLAS [13] and the proposed methods. More results can be found in the supplementary material.
[15] J. Kwon and K. M. Lee. Visual tracking decomposition. In CVPR, pages 1269– 1276, 2010.
[16] X. Li, W. Hu, Z. Zhang, X. Zhang, M. Zhu, and J. Cheng. Visual tracking via incremental log-Euclidean Riemannian subspace learning. In CVPR, pages 1–8, 2008.
[17] B. Liu, J. Huang, L. Yang, and C. A. Kulikowski. Robust tracking using local sparse appearance model and k-selection. In CVPR, pages 13 13–1320, 2011.
[18] H. Lu, S. Lu, D. Wang, S. Wang, and H. Leung. Pixel-wise spatial pyramidbased hybrid tracking. TCSVT, 22(9): 1365–1376, 2012.
[19] X. Mei and H. Ling. Robust visual tracking using ?1 minimization. In ICCV, pages 1436–1443, 2009.
[20] D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental learning for robust visual tracking. IJCV, 77(1-3): 125–141, 2008.
[21] J. Santner, C. Leistner, A. Saffari, T. Pock, and H. Bischof. PROST: Parallel robust online simple tracking. In CVPR, pages 723–730, 2010.
[22] E. J. Schlossmacher. An iterative technique for absolute deviations curve fitting. JOSA, 68(344):857–859, 1973.
[23] I. W. Selesnick. The estimation of laplace random vectors in additive white gaussian noise. TSP, 56(8-1):3482–3496, 2008.
[24] D. Wang and H. Lu. Object tracking via 2DPCA and ?1-regularization. SPL, 19(1 1):71 1–714, 2012.
[25] D. Wang and H. Lu. On-line learning parts-based representation via incremental orthogonal projective non-negative matrix factorization. SP, 93: 1608–1623, 2013.
[26] D. Wang, H. Lu, and M.-H. Yang. Online object tracking with sparse prototypes. TIP, 22(1):314–325, 2013.
[27] S. Wang, H. Lu, F. Yang, and M.-H. Yang. Superpixel tracking. In ICCV, pages 1323–1330, 2011.
[28] J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry, and Y. Ma. Robust face recognition via sparse representation. TPAMI, 3 1(2):210–227, 2009.
[29] Y. Wu, H. Ling, J. Yu, F. Li, X. Mei, and E. Cheng. Blurred target tracking by blur-driven tracker. In ICCV, pages 1100–1 107, 2011.
[30] K. Zhang, L. Zhang, and M.-H. Yang. Real-time compressive tracking. In ECCV, pages 864–877, 2012.
[31] T. Zhang, B. Ghanem, S. Liu, and N. Ahuja. Robust visual tracking via multitask sparse learning. In CVPR, pages 2042–2049, 2012.
[32] W. Zhong, H. Lu, and M.-H. Yang. Robust object tracking via sparsity-based collaborative model. In CVPR, pages 1838–1845, 2012. 222333777866