基于粒子滤波跟踪方法研究

Study on Particle Filter Based Tracking Method

文章针对道路上的车辆跟踪问题,提出了粒子滤波跟踪算法。粒子滤波通过非参数化的蒙特卡罗模拟方法来实现递推贝叶斯滤波,适用于任何能用状态空间模型表示的非线性系统,以及传统卡尔曼滤波无法表示的非线性系统,精度可以逼进最优估计。粒子滤波方法的使用非常灵活,容易实现,具有并行结构,实用性强。文章的主要研究内容包括粒子滤波理论及其实现方法;利用粒子滤波理论来解决目标跟踪问题,构建基于粒子滤波的跟踪框架。

This dissertation is an exploration on particle filter based Visual Tracking method. The aim is to improve the tracking stability under complex background and propose a practical method to track deformable object. Particle filter realizes recursive Bayesian filter via Monte Carlo simulation. The method is suitable for any non-linear system that could be represented with state model. It is more practical than conventional Kalman filter and its precision could approach optimal estimation. Particle filter is flexible and easy to be implemented. And it has a parallel structure. This dissertation studies on the particle filter and its implementation. The method is used to solve tracking problem and the tracking framework is formed accordingly.