Abrupt motion tracking via adaptive stochastic approximation Monte Carlo sampling

Robust tracking of abrupt motion is a challenging task in computer vision due to the large motion uncertainty. In this paper, we propose a stochastic approximation Monte Carlo (SAMC) based tracking scheme for abrupt motion problem in Bayesian filtering framework. In our tracking scheme, the particle weight is dynamically estimated by learning the density of states in simulations, and thus the local-trap problem suffered by the conventional MCMC sampling-based methods could be essentially avoided. In addition, we design an adaptive SAMC sampling method to further speed up the sampling process for tracking of abrupt motion. It combines the SAMC sampling and a density grid based statistical predictive model, to give a data-mining mode embedded global sampling scheme. It is computationally efficient and effective in dealing with abrupt motion difficulties. We compare it with alternative tracking methods. Extensive experimental results showed the effectiveness and efficiency of the proposed algorithm in dealing with various types of abrupt motions.

[1]  Rama Chellappa,et al.  Visual tracking and recognition using appearance-adaptive models in particle filters , 2004, IEEE Transactions on Image Processing.

[2]  Michael Isard,et al.  Object localization by Bayesian correlation , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  R. Carroll,et al.  Stochastic Approximation in Monte Carlo Computation , 2007 .

[4]  Patrick Pérez,et al.  Color-Based Probabilistic Tracking , 2002, ECCV.

[5]  H. Haario,et al.  An adaptive Metropolis algorithm , 2001 .

[6]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[7]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, CVPR.

[8]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[9]  Ramakant Nevatia,et al.  Tracking multiple humans in crowded environment , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[10]  Gareth O. Roberts,et al.  Examples of Adaptive MCMC , 2009 .

[11]  Faming Liang,et al.  Adaptive evolutionary Monte Carlo algorithm for optimization with applications to sensor placement problems , 2008, Stat. Comput..

[12]  D. Landau,et al.  Efficient, multiple-range random walk algorithm to calculate the density of states. , 2000, Physical review letters.

[13]  Eric Moulines,et al.  Stability of Stochastic Approximation under Verifiable Conditions , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[14]  J. Rosenthal,et al.  Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms , 2007, Journal of Applied Probability.

[15]  Frank Dellaert,et al.  An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets , 2004, ECCV.

[16]  Junseok Kwon,et al.  Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation , 2008, ECCV.

[17]  Ming Yang,et al.  Tracking non-stationary appearances and dynamic feature selection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  Michael Isard,et al.  A mixed-state condensation tracker with automatic model-switching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[19]  Yuan Li,et al.  Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Faming Liang,et al.  A Theory for Dynamic Weighting in Monte Carlo Computation , 2001 .

[21]  Gang Hua,et al.  Multi-scale visual tracking by sequential belief propagation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..