Incremental density approximation and kernel-based Bayesian filtering for object tracking

Statistical density estimation techniques are used in many computer vision applications such as object tracking, background subtraction, motion estimation and segmentation. The particle filter (condensation) algorithm provides a general framework for estimating the probability density functions (pdf) of general non-linear and non-Gaussian systems. However, since this algorithm is based on a Monte Carlo approach, where the density is represented by a set of random samples, the number of samples is problematic, especially for high dimensional problems. In this paper, we propose an alternative to the classical particle filter in which the underlying pdf is represented with a semi-parametric method based on a mode finding algorithm using mean-shift. A mode propagation technique is designed for this new representation for tracking applications. A quasi-random sampling method in the measurement stage is used to improve performance, and sequential density approximation for the measurements distribution is performed for efficient computation. We apply our algorithm to a high dimensional color-based tracking problem, and demonstrate its performance by showing competitive results with other trackers.