一种快速估计线性非线性状态的粒子滤波器  

A Fast Estimating Linear/Nonlinear Condition Particle Filter

作　　者：刘元魁[1] 樊养余[1] 赵炯[1] 黄爱萍[1] 

机构地区：[1]西北工业大学电子信息学院,陕西西安710129

出　　处：《测控技术》2009年第5期75-77,共3页Measurement & Control Technology

基　　金：国家863计划资助项目(2007AA01Z234);陕西省自然科学基金资助项目(2007F10)

摘　　要：提出了一种快速估计线性一非线性状态的粒子滤波器。针对混合线性一非线性模型中传统的Rao-Blackwellized Particle Filter（RBPF）方法对状态估计处理速度较慢的不足，将条件相关的线性与非线性状态进行分离，对于非线性状态运用粒子滤波（PF）算法进行估计，取出从非线性状态中抽取出的粒子的均值，将此均值传播到线性状态中做一次卡尔曼滤波，得出对线性状态的估计。仿真结果表明：与RBPF相比可以将处理速度提高50％～60％，有效改善状态估计的实时性。A fast estimating linear/non-linear condition particle filter algorithm is presented. The new method separates the related linear and non-linear conditions to overcome the RBPF（ Rao-Blaekwellized particle filter） algorithm shortage on processing speed in the mixed linear/non-linear model, for the estimation of non-linear condition, traditional particle filter is used, and the mean of the particles drawn from the non-linear condition is computed and propagated to the linear part to get the estimation. The simulation shows that compared with RBPF, the new method can improve the processing speed by 50% - 60% and the real-time application effectively.

关 键 词：目标跟踪 粒子滤波器 混合线性/非线性 处理速度 

分 类 号：TN911.2[电子电信—通信与信息系统]