粒子滤波器和其在目标跟踪中的应用.pdf

3 Vol. 1 No. 3 2003 10 Radar Science and Technology October 2003 , ( ATR , 410073) : 为了在物理条件下对目标进行精确建模, 有时需要运用非线性非高斯系统而 规的卡尔 曼滤波算法要求系统是线性高斯型的, 因而不能直接用来解决非线性非高斯问题为了解决这 一问题, 人们开发出各种非线性滤波算法一种是扩展卡尔曼算法(EKF) , 它对非线性系统进行局部线性化, 从而 间接利用卡尔曼算法进行滤波与估算; 另一种是序列蒙特卡罗算法, 亦即粒子滤波器( PF) , 它是最近出现 的解决非线性问题的有效算法本文简要介绍非线性跟踪的最优与次优贝叶斯算法, 重点关注粒子滤波 器, 通过再入大气层弹道目标的例子, 说明PF 在目标跟踪中的应用 : 目标跟踪; 非线性系统; 贝叶斯算法; 粒子滤波器 :TN953 :A : 1 722337(2003) Particle Filter for Target Tracking JIANG Baoan, LU Huanzhang ( National K ey Lab of ATR , N UDT , Changsha 410073, China) Abstract: For many applications, it is becoming important to involve some elements with nonlinearity and non Gaussionity in order to model accurately the underlying dynamics of a physical system. Moreover, in this case, it is usu ally difficult to directly utilize Kalman filter( KF) , because KF is based on condition of linearGaussian system. For solv ing these problems, several variants of nonlinear/ nonGaussian filters are developed. One is extended Kalman filter ( EKF) , it makes a local linearization to a nonlinear system, so KF can be utilized indirectly to filter and estimate.The other is sequential Monte Carlo method based on point mass,which is called particle filter( PF) . It is an efficient method dealing with nonlinear/ nonGaussian problems. In this paper, we review both optimum and suboptimum Bayesian algorithms for nonlinear tracking problems, with focus on PF. And the performances of the PF are discussed and com pared with the EKF through tracking a reentry ballistic object. Key words: target tracking; nonlinear system; Bayesian algorithm; particle filter