非线性滤波算法性能对比

Performances comparison on nonlinear filtering algorithms

随着目标运动的多样性和复杂化,雷达非线性目标跟踪算法越来越受到重视。本文对目前非线性滤波的主要算法即扩展卡尔曼滤波、不敏卡尔曼滤波、粒子滤波的滤波模型、适用条件、性能进行了分析比较,通过一个非线性非高斯模型进行了仿真,验证了这些算法的性能,仿真结果表明非线性条件下粒子滤波算法要明显优于其它两种滤波算法。

With the goal of the diversity and complexity of motion,nonlinear target tracking of radar is paid more and more attention.This paper present the main algorithms of the nonlinear filter extended Kalman filter,Unscented Kalman filter,particle filter the filter model,applicable conditions,performance is analyzed and compared,a non-linear and non-Gaussian model was simulated to verify the performance of these algorithms,simulation results show that the particle filter under nonlinear conditions is much better than the other two filtering algorithms.