cvpr cvpr2013 cvpr2013-121 cvpr2013-121-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Anton Milan, Konrad Schindler, Stefan Roth
Abstract: When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be assigned at most one observation per frame; (2) in trajectory estimation, two trajectories should remain spatially separated at all times to avoid collisions. Yet, existing trackers often sidestep these important constraints. We address this using a mixed discrete-continuous conditional randomfield (CRF) that explicitly models both types of constraints: Exclusion between conflicting observations with supermodular pairwise terms, and exclusion between trajectories by generalizing global label costs to suppress the co-occurrence of incompatible labels (trajectories). We develop an expansion move-based MAP estimation scheme that handles both non-submodular constraints and pairwise global label costs. Furthermore, we perform a statistical analysis of ground-truth trajectories to derive appropriate CRF potentials for modeling data fidelity, target dynamics, and inter-target occlusion.
[1] B. Andres, T. Beier, and J. Kappes. OpenGM: A C++ library for discrete graphical models. arXiv:1206.0111, 2012.
[2] M. Andriluka, S. Roth, and B. Schiele. Monocular 3D pose estimation and tracking by detection. CVPR 2010.
[3] A. Andriyenko and K. Schindler. Multi-target tracking by continuous energy minimization. CVPR 2011.
[4] A. Andriyenko, K. Schindler, and S. Roth. Discrete-continuous optimization for multi-target tracking. CVPR 2012.
[5] J. Berclaz, F. Fleuret, and P. Fua. Multiple object tracking using flow linear programming. Winter-PETS, 2009.
[6] J. Bergstra and Y. Bengio. Random search for hyperparameter optimization. JMLR, 13:281–305, 2012.
[7] K. Bernardin and R. Stiefelhagen. Evaluating multiple object tracking performance: The CLEAR MOT metrics. Image and Video Processing, 2008(1): 1–10, 2008.
[8] M. D. Breitenstein, F. Reichlin, B. Leibe, E. Koller-Meier, and L. Van Gool. Robust tracking-by-detection using a detector confidence particle filter. ICCV 2009.
[9] W. Brendel, M. Amer, and S. Todorovic. Multiobject tracking as maximum weight independent set. CVPR 2011.
[10] I. J. Cox. A review of statistical data association techniques for motion correspondence. IJCV, 10(1):53–66, 1993.
[11] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. CVPR 2005.
[12] A. Delong, A. Osokin, H. N. Isack, and Y. Boykov. Fast approximate energy minimization with label costs. IJCV, 96(1): 1–27, 2012.
[13] A. Ess, B. Leibe, K. Schindler, and L. Van Gool. A mobile vision system for robust multi-person tracking. CVPR 2008.
[14] J. M. Ferryman and A. Shahrokni. PETS2009: Dataset and challenge. Winter-PETS, 2009.
[15] T. E. Fortmann, Y. Bar-Shalom, and M. Scheffe. Multi-target tracking using joint probabilistic data association. IEEE Conf. on Decision and Control, 1980.
[16] H. Jiang, S. Fels, and J. J. Little. A linear programming approach for multiple object tracking. CVPR 2007.
[17] Z. Kalal, J. Matas, and K. Mikolajczyk. P-N Learning: Bootstrapping binary classifiers from unlabeled data by structural constraint. CVPR 2010.
[18] V. Kolmogorov. Convergent tree-reweighted message passing for energy minimization. PAMI, 28(10): 1568–1583, 2006.
[19] C.-H. Kuo and R. Nevatia. How does person identity recognition help multi-person tracking? CVPR 2011.
[20] L. Ladicky, C. Russell, P. Kohli, and P. Torr. Graph cut based
[21]
[22]
[23]
[24]
[25]
[26] inference with co-occurrence statistics. ECCV 2010. H. Pirsiavash, D. Ramanan, and C. C. Fowlkes. Globallyoptimal greedy algorithms for tracking a variable number of objects. CVPR 2011. J. Vermaak, A. Doucet, and P. P ´erez. Maintaining multimodality through mixture tracking. ICCV 2003. Z. Wu, T. H. Kunz, and M. Betke. Efficient track linking methods for track graphs using network-flow and set-cover techniques. CVPR 2011. B. Yang and R. Nevatia. An online learned CRF model for multi-target tracking. CVPR 2012. A. R. Zamir, A. Dehghan, and M. Shah. GMCP-Tracker: Global multi-object tracking using generalized minimum clique graphs. ECCV 2012. L. Zhang, Y. Li, and R. Nevatia. Global data association for multi-object tracking using network flows. CVPR 2008. 333666888977