Kernel-based Bayesian filtering for object tracking

TitleKernel-based Bayesian filtering for object tracking
Publication TypeConference Papers
Year of Publication2005
AuthorsHan B, Zhu Y, Comaniciu D, Davis LS
Conference NameComputer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
Date Published2005/06//
Keywordsapproach;, approximation;, Bayes, Bayesian, Carlo, density, detection;, filtering;, functions;, Gaussian, interpolation;, kernel-based, methods;, mixtures;, Monte, nonGaussian, nonlinear, object, particle, probability, probability;, processes;, recognition;, sampling, sampling;, sequences;, system;, tracking;, video

Particle filtering provides a general framework for propagating probability density functions in nonlinear 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 kernel-based 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 real-time tracking problems, and demonstrate its performance on real video sequences as well as synthetic examples.