Abstract
We propose a novel tracking algorithm based on the Wang-Landau Monte Carlo sampling method which efficiently deals with the abrupt motions. Abrupt motions could cause conventional tracking methods to fail since they violate the motion smoothness constraint. To address this problem, we introduce the Wang-Landau algorithm that has been recently proposed in statistical physics, and integrate this algorithm into the Markov Chain Monte Carlo based tracking method. Our tracking method alleviates the motion smoothness constraint utilizing both the likelihood term and the density of states term, which is estimated by the Wang-Landau algorithm. The likelihood term helps to improve the accuracy in tracking smooth motions, while the density of states term captures abrupt motions robustly. Experimental results reveal that our approach efficiently samples the object’s states even in a whole state space without loss of time. Therefore, it tracks the object of which motion is drastically changing, accurately and robustly.
Chapter PDF
References
Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Comput. Surv. 38(4) (2006)
Cai, Y., de Freitas, N., Little, J.: Robust visual tracking for multiple targets. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 107–118. Springer, Heidelberg (2006)
Isard, M., Blake, A.: Icondensation: Unifying low-level and high-level tracking in a stochastic framework. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407. Springer, Heidelberg (1998)
Khan, Z., Balch, T., Dellaert, F.: An mcmc-based particle filter for tracking multiple interacting targets. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 279–290. Springer, Heidelberg (2004)
Smith, K., Perez, D.G., Odobez, J.: Using particles to track varying numbers of interacting people. In: CVPR (2005)
Zhao, T., Nevatia, R.: Tracking multiple humans in crowded environment. In: CVPR (2004)
Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. IJCV 75(2), 247–266 (2007)
Nillius, P., Sullivan, J., Carlsson, S.: Multi-target tracking: Linking identities using bayesian network inference. In: CVPR (2006)
Jepson, A., Fleet, D., Maraghi, T.E.: Robust online appearance models for visual tracking. PAMI 25(10), 1296–1311 (2003)
Yang, M., Wu, Y.: Tracking non-stationary appearances and dynamic feature selection. In: CVPR (2005)
Han, B., Davis, L.: On-line density-based appearance modeling for object tracking. In: ICCV (2005)
Wang, F., Landau, D.: Efficient, multiple-range random walk algorithm to calculate the density of states. Phys. Rev. Lett. 86(10), 2050–2053 (2001)
Philomin, V., Duraiswami, R., Davis, L.: Quasi-Random Sampling for Condensation. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 134–149. Springer, Heidelberg (2000)
Li, Y., Ai, H., Yamashita, T., Lao, S., Kawade, M.: Tracking in low frame rate video: A cascade particle filter with discriminative observers of different lifespans. In: CVPR (2007)
Atchade, Y., Liu, J.: The wang-landau algorithm for monte carlo computation in general state spaces. Technical Report (2004)
Perez, P., Hue, C., Vermaak, J., Gangnet, M.: Color-based probabilistic tracking. In: Tistarelli, M., Bigun, J., Jain, A.K. (eds.) ECCV 2002. LNCS, vol. 2359, pp. 661–675. Springer, Heidelberg (2002)
Roberts, G., Rosenthal, J.: Examples of adaptive mcmc (preprint, 2006)
Berg, B.: Introduction to markov chain monte carlo simulations and their statistical analysis. Phys.Stat. Mech. (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Electronic Supplementary Material
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kwon, J., Lee, K.M. (2008). Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5302. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88682-2_30
Download citation
DOI: https://doi.org/10.1007/978-3-540-88682-2_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88681-5
Online ISBN: 978-3-540-88682-2
eBook Packages: Computer ScienceComputer Science (R0)