The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.04 - April (2013 vol.35)
pp: 1011-1024
Junseok Kwon , Dept. of Electr. Eng. & Comput. Sci., Seoul Nat. Univ., Seoul, South Korea
Kyoung Mu Lee , Dept. of Electr. Eng. & Comput. Sci., Seoul Nat. Univ., Seoul, South Korea
ABSTRACT
We propose a novel tracking algorithm based on the Wang-Landau Monte Carlo (WLMC) sampling method for dealing with abrupt motions efficiently. Abrupt motions cause conventional tracking methods to fail because they violate the motion smoothness constraint. To address this problem, we introduce the Wang-Landau sampling method and integrate it into a Markov Chain Monte Carlo (MCMC)-based tracking framework. By employing the novel density-of-states term estimated by the Wang-Landau sampling method into the acceptance ratio of MCMC, our WLMC-based tracking method alleviates the motion smoothness constraint and robustly tracks the abrupt motions. Meanwhile, the marginal likelihood term of the acceptance ratio preserves the accuracy in tracking smooth motions. The method is then extended to obtain good performance in terms of scalability, even on a high-dimensional state space. Hence, it covers drastic changes in not only position but also scale of a target. To achieve this, we modify our method by combining it with the N-fold way algorithm and present the N-Fold Wang-Landau (NFWL)-based tracking method. The N-fold way algorithm helps estimate the density-of-states with a smaller number of samples. Experimental results demonstrate that our approach efficiently samples the states of the target, even in a whole state space, without loss of time, and tracks the target accurately and robustly when position and scale are changing severely.
INDEX TERMS
Target tracking, Proposals, Monte Carlo methods, Sampling methods, Markov processes, Robustness,Markov Chain Monte Carlo, Object tracking, abrupt motion, Wang-Landau method, density-of-states, N-fold way
CITATION
Junseok Kwon, Kyoung Mu Lee, "Wang-Landau Monte Carlo-Based Tracking Methods for Abrupt Motions", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.35, no. 4, pp. 1011-1024, April 2013, doi:10.1109/TPAMI.2012.161
REFERENCES
[1] A. Yilmaz, O. Javed, and M. Shah, "Object Tracking: A Survey," ACM Computing Surveys, vol. 38, no. 4,article 13, 2006.
[2] S. Avidan, "Ensemble Tracking," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 2, pp. 261-271, Feb. 2007.
[3] B. Babenko, M. Yang, and S. Belongie, "Visual Tracking with Online Multiple Instance Learning," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
[4] R.T. Collins, Y. Liu, and M. Leordeanu, "Online Selection of Discriminative Tracking Features," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1631-1643, Oct. 2005.
[5] H. Grabner and H. Bischof, "On-Line Boosting and Vision," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2006.
[6] B. Han and L. Davis, "On-Line Density-Based Appearance Modeling for Object Tracking," Proc. 10th IEEE Int'l Conf. Computer Vision, 2005.
[7] A.D. Jepson, D.J. Fleet, and T.F.E. Maraghi, "Robust Online Appearance Models for Visual Tracking," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1296-1311, Oct. 2003.
[8] J. Kwon and K.M. Lee, "Tracking of a Non-Rigid Object via Patch-Based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte Carlo Sampling," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
[9] D.A. Ross, J. Lim, R. Lin, and M. Yang, "Incremental Learning for Robust Visual Tracking," Int'l J. Computer Vision, vol. 77, nos. 1-3, pp. 125-141, 2008.
[10] M. Yang and Y. Wu, "Tracking Non-Stationary Appearances and Dynamic Feature Selection," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2005.
[11] A. Adam, E. Rivlin, and I. Shimshoni, "Robust Fragments-Based Tracking Using the Integral Histogram," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2006.
[12] D. Comaniciu, V. Ramesh, and P. Meer, "Real-Time Tracking of Non-Rigid Objects Using Mean Shift," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2000.
[13] J. Kwon, K.M. Lee, and F.C. Park, "Visual Tracking via Geometric Particle Filtering on the Affine Group with Optimal Importance Functions," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2009.
[14] B. Leibe, K. Schindler, N. Cornelis, and L. Van Gool, "Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 10, pp. 1683-1698, Oct. 2008.
[15] F. Wang and D. Landau, "Efficient, Multiple-Range Random Walk Algorithm to Calculate the Density of States," Physics Rev. Letters, vol. 86, no. 10, pp. 2050-2053, 2001.
[16] L.P. Kaelbling, M.L. Littman, and A.W. Moore, "Reinforcement Learning: A Survey," J. Artificial Intelligence Research, vol. 4, no. 1, pp. 237-285, 1996.
[17] J. Kwon and K.M. Lee, "Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation," Proc. European Conf. Computer Vision, 2008.
[18] B.A. Berg and T. Neuhaus, "Multicanonical Algorithms for First Order Phase Transitions," Physics Letter B, vol. 267, no. 2, pp. 249-253, 1991.
[19] B. Schulz, K. Binder, and M. Mueller, "Flat Histogram Method of Wang-Landau and N-Fold Way," Int'l J. Modern Physics C, vol. 13, no. 4, pp. 477-494, 2002.
[20] M. Isard and A. Blake, "Icondensation: Unifying Low-Level and High-Level Tracking in a Stochastic Framework," Proc. European Conf. Computer Vision, 1998.
[21] P. Perez, C. Hue, J. Vermaak, and M. Gangnet, "Color-Based Probabilistic Tracking," Proc. European Conf. Computer Vision, 2002.
[22] Y. Li, H. Ai, T. Yamashita, S. Lao, and M. Kawade, "Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2007.
[23] M. Isard and J. MacCormick, "Bramble: A Bayesian Multi-Blob Tracker," Proc. Eighth IEEE Int'l Conf. Computer Vision, 2001.
[24] J. MacCormick and A. Blake, "Probabilistic Exclusion Principle for Tracking Multiple Objects," Proc. Seventh IEEE Int'l Conf. Computer Vision, 1999.
[25] Z. Khan, T. Balch, and F. Dellaert, "MCMC-Based Particle Filtering for Tracking a Variable Number of Interacting Targets," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 11, pp. 1805-1918, Nov. 2005.
[26] K. Smith, D.G. Perez, and J. Odobez, "Using Particles to Track Varying Numbers of Interacting People," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2005.
[27] T. Zhao and R. Nevatia, "Tracking Multiple Humans in Crowded Environment," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2004.
[28] G. Hua and Y. Wu, "Multi-Scale Visual Tracking by Sequential Belief Propagation," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2004.
[29] V. Philomin, R. Duraiswami, and L. Davis, "Quasi-Random Sampling for Condensation," Proc. European Conf. Computer Vision, 2000.
[30] G. Roberts and J. Rosenthal, "Examples of Adaptive MCMC," J. Computational and Graphical Statistics, vol. 18, no. 2, pp. 349-367, 2009.
[31] G. Roberts, A. Gelman, and W. Gilks, "Weak Convergence and Optimal Scaling of Random Walk Metropolis Algorithms," Ann. Applied Probability, vol. 7, no. 1, pp. 110-120, 1997.
[32] W. Li, X. Zhang, and W. Hu, "Contour Tracking with Abrupt Motion," Proc. 16th IEEE Int'l Conf. Image Processing, 2009.
[33] X. Zhou and Y. Lu, "Abrupt Motion Tracking via Adaptive Stochastic Approximation Monte Carlo Sampling," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2010.
[34] W. Hastings, "Monte Carlo Sampling Methods Using Markov Chains and Their Applications," Biometrika, vol. 57, pp. 97-109, 1970.
[35] N.d.F. Yizheng Cai and J.J. Little, "Robust Visual Tracking for Multiple Targets," Proc. European Conf. Computer Vision, 2006.
[36] H. Ling and K. Okada, "Diffusion Distance for Histogram Comparison," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2006.
[37] R. Belardinelli and V. Pereyra, "Wang-Landau Algorithm: A Theoretical Analysis of the Saturation of the Error," J. Chemical Physics, vol. 127, no. 18, p. 184105, 2007.
[38] J. Kwon and K.M. Lee, "Visual Tracking Decomposition," Proc. IEEE Conf. Computer Vision and Computer Recognition, 2010.
57 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool