iccv iccv2013 iccv2013-58 iccv2013-58-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ernesto Brau, Jinyan Guan, Kyle Simek, Luca Del Pero, Colin Reimer Dawson, Kobus Barnard
Abstract: Jinyan Guan† j guan1 @ emai l ari z ona . edu . Kyle Simek† ks imek@ emai l ari z ona . edu . Colin Reimer Dawson‡ cdaws on@ emai l ari z ona . edu . ‡School of Information University of Arizona Kobus Barnard‡ kobus @ s i sta . ari z ona . edu ∗School of Informatics University of Edinburgh for tracking an unknown and changing number of people in a scene using video taken from a single, fixed viewpoint. We develop a Bayesian modeling approach for tracking people in 3D from monocular video with unknown cameras. Modeling in 3D provides natural explanations for occlusions and smoothness discontinuities that result from projection, and allows priors on velocity and smoothness to be grounded in physical quantities: meters and seconds vs. pixels and frames. We pose the problem in the context of data association, in which observations are assigned to tracks. A correct application of Bayesian inference to multitarget tracking must address the fact that the model’s dimension changes as tracks are added or removed, and thus, posterior densities of different hypotheses are not comparable. We address this by marginalizing out the trajectory parameters so the resulting posterior over data associations has constant dimension. This is made tractable by using (a) Gaussian process priors for smooth trajectories and (b) approximately Gaussian likelihood functions. Our approach provides a principled method for incorporating multiple sources of evidence; we present results using both optical flow and object detector outputs. Results are comparable to recent work on 3D tracking and, unlike others, our method requires no pre-calibrated cameras.
[1] M. Andriluka, S. Roth, and B. Schiele. Monocular 3d pose estimation and tracking by detection. In CVPR, pages 623– 630, 2010. 1
[2] A. Andriyenko, S. Roth, and K. Schindler. An analytical formulation of global occlusion reasoning for multi-target tracking. In ICCV Workshop, pages 1839–1846, 2011. 7 33336747
[3] A. Andriyenko and K. Schindler. Globally optimal multitarget tracking on a hexagonal lattice. In ECCV, pages 466– 479, 2010. 2
[4] A. Andriyenko and K. Schindler. Multi-target tracking by continuous energy minimization. In CVPR, 2011. 1, 2, 7
[5] A. Andriyenko, K. Schindler, and S. Roth. Discretecontinuous optimization for multi-target tracking. In CVPR, pages 1926–1933, 2012. 1, 2, 7
[6] B. Benfold and I. Reid. Stable multi-target tracking in realtime surveillance video. In CVPR, pages 3457–3464, 2011. 1
[7] M. Betke, D. E. Hirsh, A. Bagchi, N. I. Hristov, N. C. Makris, and T. H. Kunz. Tracking large variable numbers of objects in clutter. In CVPR, 2007. 2
[8] E. Brau, K. Barnard, R. Palanivelu, D. Dunatunga, T. Tsukamoto, and P. Lee. A generative statistical model for tracking multiple smooth trajectories. In CVPR, pages 1137–1 144, 2011. 2, 5
[9] P. Carr, Y. Sheikh, and I. Matthews. Monocular object de-
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19]
[20] tection using 3d geometric primitives. In ECCV, pages 864– 878, Berlin, Heidelberg, 2012. Springer-Verlag. 2 W. Choi and S. Savarese. Multiple target tracking in world coordinate with single, minimally calibrated camera. ECCV, pages 553–567, 2010. 2 K. Choo and D. Fleet. People tracking with hybrid monte carlo. ICCV, II:321–328, 2001. 2 L. Del Pero, J. Guan, E. Brau, J. Schlecht, and K. Barnard. Sampling bedrooms. CVPR, pages 2009–2016, 2011. 4, 6 A. Ess, B. Leibe, K. Schindler, and L. van Gool. Robust multiperson tracking from a mobile platform. IEEE PAMI, 31(10): 183 1–1846, October 2009. 2 P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained partbased models. IEEE PAMI, 2009. 2, 6 M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. of the ACM, 24:381–395, 1981. 7 F. Fleuret, J. Berclaz, R. Lengagne, and P. Fua. Multi-camera people tracking with a probabilistic occupancy map. IEEE PAMI, 2007. 2 W. Gilks, S. Richardson, and D. Spiegelhalter. Introducing markov chain monte carlo. In W. Gilks, S. Richardson, and D. Spiegelhalte, editors, Markov chain Monte Carlo in practice. Chapman and Hall, 1996. 6 R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2000. 4 D. Hoiem, A. A. Efros, and M. Hebert. Putting objects in perspective. In CVPR, 2006. 2 M. Isard and A. Blake. Condensation – conditional density
[21]
[22]
[23]
[24]
[25]
[26]
[27]
[28]
[29]
[30] [3 1] propagation for visual tracking. Int. J. Comp. Vis., 29(1):5– 28, 1998. 1 M. Isard and J. MacCormick. Bramble: A bayesian multipleblob tracker. In ICCV, pages 34–41, 2001 . 2 Z. Khan, T. Balch, and F. Dellaert. Mcmc-based particle filtering for tracking a variable number of interacting targets. PAMI, 27(1 1): 1805–1819, 2005. 1 C. Kuo, C. Huang, and R. Nevatia. Multi-target tracking by on-line learned discriminative appearance models. In CVPR, pages 685–692, 2010. 1 S. Kwak, W. Nam, B. Han, and J. H. Han. Learning occlusion with likelihoods for visual tracking. ICCV, 2011. 1 Y. Li, C. Huang, and R. Nevatia. Learning to associate: Hybridboosted multi-target tracker for crowded scene. CVPR, 2000. 7 C. Liu. Exploring New Representations and Applications for Motion Analysis. PhD thesis, M.I.T., 2009. 2, 6 M. A. McDowell, C. D. Fryar, R. Hirsch, and C. L. Ogden. Anthropometric reference data for children and adults: U.s. population, 1999–2002. Advance Data, (361), July 2005. 3 R. Mohedano and N. Garcia. Simultaneous 3d object tracking and camera parameter estimation by bayesian methods and transdimensional mcmc sampling. In ICIP, 2011. 2 R. M. Neal. Probabilistic inference using markov chain monte carlo methods. Technical report, 1993. 6 S. Oh. Bayesian formulation of data association and markov chain monte carlo data association. In Robotics: Science and Systems Conference (RSS) Workshop Inside Data association, 2008. 2 S. Oh, S. Russell, and S. Sastry. Markov chain Monte Carlo data association for general multiple target tracking prob-
[32]
[33]
[34]
[35]
[36]
[37]
[38]
[39]
[40]
[41]
[42] lems. 2004. 1, 2, 5 K. Okuma, A. Taleghani, N. d. Freitas, J. Little, and D. Lowe. A boosted particle filter: Multitarget detection and tracking. In ECCV, 2004. 1 C. E. Rasmussen and C. K. I. Williams. Gaussian Processes For Machine Learning. MIT Press, 2006. 3 A. Roshan Zamir, A. Dehghan, and M. Shah. Gmcp-tracker: Global multi-object tracking using generalized minimum clique graphs. In ECCV, pages 343–356. 2012. 7 M. Seeger. Gaussian processes for machine learning. Int. J. of Neural Systems, 14(2):69–106, 2004. 3 H. Sidenbladh, M. Black, and D. Fleet. Stochastic tracking of 3d human figures using 2d image motion. ECCV, II:702– 718, 2000. 2 C. Sminchisescu and B. Triggs. Kinematic jump processes for monocular 3d human tracking. In CVPR, 2003. 2 R. Stiefelhagen, K. Bernardin, R. Bowers, J. Garofolo, D. Mostefa, and P. Soundararajan. The clear 2006 evaluation. In Proceedings of the 1st international evaluation conference on Classification of events, activities and relationships, CLEAR’06, pages 1–44, Berlin, Heidelberg, 2007. 7 C. Wojek, S. Roth, K. Schindler, and B. Schiele. Monocular 3d scene modeling and inference: Understanding multiobject traffic scenes. ECCV, pages 467–481, 2010. 1, 2 Z. Wu, T. H. Kunz, and M. Betke. Efficient track linking methods for track graphs using network-flow and set-cover techniques. CVPR, pages 1185–1 192, 2011. 2 Z. Wu, A. Thangali, S. Sclaroff, and M. Betke. Coupling detection and data association for multiple object tracking. CVPR, pages 1948–1955, june 2012. 1, 7 X. Yan, X. Wu, I. A. Kakadiaris, and S. K. Shah. To track or to detect? an ensemble framework for optimal selection. In ECCV, pages 594–607, 2012. 7 33336758