cvpr cvpr2013 cvpr2013-301 cvpr2013-301-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Xinchu Shi, Haibin Ling, Junling Xing, Weiming Hu
Abstract: In this paper we formulate multi-target tracking (MTT) as a rank-1 tensor approximation problem and propose an ?1 norm tensor power iteration solution. In particular, a high order tensor is constructed based on trajectories in the time window, with each tensor element as the affinity of the corresponding trajectory candidate. The local assignment variables are the ?1 normalized vectors, which are used to approximate the rank-1 tensor. Our approach provides a flexible and effective formulation where both pairwise and high-order association energies can be used expediently. We also show the close relation between our formulation and the multi-dimensional assignment (MDA) model. To solve the optimization in the rank-1 tensor approximation, we propose an algorithm that iteratively powers the intermediate solution followed by an ?1 normalization. Aside from effectively capturing high-order motion information, the proposed solver runs efficiently with proved convergence. The experimental validations are conducted on two challenging datasets and our method demonstrates promising performances on both.
[1] CLIF dataset. www.sdms.afrl.af.mil/index.php?collection=clif2006. 6
[2] M. Andriluka, S. Roth, and B. Schiele. People-tracking-by-detection and people-detection-by-tracking. In CVPR, 2008. 1
[3] Y. Bar-Shalom and T. Fortmann. Tracking anddata association. Academic Press., 1988. 2
[4] B. Benfold and I. Reid. Stable multi-target tracking in real-time surveillance video. In CVPR, 2011. 2
[5] J. Berclaz, F. Fleuret, E. Turetken, and P. Fua. Multiple object tracking using k-shortest paths optimization. TPAMI, 33(9): 1806–1819, 2011. 1, 2, 5
[6] M. D. Breitenstein, F. Reichlin, B. Leibe, E. Koller-Meier, and L. Van Gool. Online multi-person tracking-by-detection from a single, uncalibrated camera. TPAMI, 33(9): 1820–1833, 2010. 1
[7] W. Brendel, M. Amer, and S. Todorovic. Multiobject tracking as maximum weight independent set. In CVPR, 2011. 1, 2
[8] R. Collins. Multitarget data association with higher-order motion models. In CVPR, 2012. 2, 6, 7
[9] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. 1, 6
[10] L. De Lathauwer, B. De Moor, and J. Vandewalle. On the best rank-1 and rank-(r 1, r 2,..., rn) approximation of higher-order tensors. SIAM J. Matrix Anal. Appl., 21(4): 1324–1342, 2000. 3
[11] S. Deb, M. Yeddanapudi, K. Pattipati, and Y. Bar-Shalom. A generalized sd assignment algorithm for multisensor-multitarget state estimation. TAES, 33(2):523–538, 1997. 1, 2
[12] O. Duchenne, F. Bach, I. Kweon, and J. Ponce. A tensor-based algorithm for high-order graph matching. TPAMI, 33(12):2383–2395, 2011. 3
[13] P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan.
[14]
[15]
[16]
[17]
[18]
[19]
[20]
[21]
[22]
[23]
[24]
[25]
[26] Object detection with discriminatively trained part-based models. TPAMI, 32(9): 1627–1645, 2010. 1 W. Ge, R. Collins, and R. Ruback. Vision-based analysis of small groups in pedestrian crowds. TPAMI, 34(5): 1003–1016, 2012. 6 C. Huang, B. Wu, and R. Nevatia. Robust object tracking by hierarchical association of detection responses. In ECCV, 2008. 1, 2 H. Jiang, S. Fels, and J. Little. A linear programming approach for multiple object tracking. In CVPR, 2007. 1, 2 S. Oh, S. Russell, and S. Sastry. Markov chain monte carlo data association for multi-target tracking. TAC, 54(3):481–497, 2009. 2 H. Pirsiavash, D. Ramanan, and C. Fowlkes. Globally-optimal greedy algorithms for tracking a variable number of objects. In CVPR, 2011. 1 A. Poore. Multidimensional assignment formulation of data association problems arising from multitarget and multisensor tracking. Comput. Optim. Appl. , 3(1):27–57, 1994. 1 P. Regalia and E. Kofidis. The higher-order power method revisited: convergence proofs and effective initialization. In ICASSP, 2000. 3 D. Reid. An algorithm for tracking multiple targets. TAC, 24(6):843– 854, 1979. 1, 2 K. Shafique, M. Lee, and N. Haering. A rank constrained continuous formulation of multi-frame multi-target tracking problem. In CVPR, 2008. 2 Z. Wu, N. Hristov, T. Hedrick, T. Kunz, and M. Betke. Tracking a large number of objects from multiple views. In CVPR, 2009. 2 J. Xing, H. Ai, L. Liu, and S. Lao. Multiple player tracking in sports video: a dual-mode two-way bayesian inference approach with progressive observation modeling. TIP, 20(6): 1652–67, 2011. 1 A. Zamir, A. Dehghan, and M. Shah. Gmcp-tracker: Global multiobject tracking using generalized minimum clique graphs. In ECCV, 2012. 1, 2 L. Zhang, Y. Li, and R. Nevatia. Global data association for multiobject tracking using network flows. In CVPR, 2008. 1 222333999422