Kernel-Based Bayesian Filtering for Object Tracking

Particle filtering provides a general framework for propagating probability density functions in non-linear and non-Gaussian systems. However, the algorithm is based on a Monte Carlo approach and sampling is a problematic issue, especially for high dimensional problems. This paper presents a new kernelbased Bayesian filtering framework, which adopts an analytic approach to better approximate and propagate density functions. In this framework, the techniques of density interpolation and density approximation are introduced to represent the likelihood and the posterior densities by Gaussian mixtures, where all parameters such as the number of mixands, their weight, mean, and covariance are automatically determined. The proposed analytic approach is shown to perform sampling more efficiently in high dimensional space. We apply our algorithm to the real-time tracking problem, and demonstrate its performance on real video sequences as well as synthetic examples.

• Type: Conference
• Year: 2005
• Where: CVPR
• Authors: Bohyung Han, Ying Zhu, Dorin Comaniciu, Larry S. Davis
• Keywords: Analytic Approach, Bayesian Filtering Framework, Computer Vision, CVPR 2005, Density Interpolation, Probability Density Functions, Propagate Density Functions