Abrupt Motion Tracking via Adaptive Stochastic Approximation Monte Carlo Sampling

Abstract

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.