Wang-Landau Monte Carlo-based Tracking Methods
for Abrupt Motions
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 whose position and scale are severely changing.
PaperTPAMI paper. (pdf)
1. Junseok Kwon and Kyoung Mu Lee. Wang-Landau Monte Carlo-based Tracking Methods for Abrupt Motions, IEEE Transaction Pattern Analysis and Machine Intelligence (TPAMI), VOL. 35, NO. 4, APRIL. 2013
2. Junseok Kwon and Kyoung Mu Lee. Tracking of Abrupt Motion using Wang-Landau Monte Carlo Estimation, European Conference on Computer Vision (ECCV), 2008 [project page]
Resultsvideo. (wmv, 45MB)
Codecode. (comming soon) dataset. (zip, 808MB)
% Other test sequences are available at [WLMC tracker]
This research is supported in part by:
- NRF Grant of MEST (314-2008-1-D00377).