基于扩展卡尔曼粒子滤波的目标跟踪算法研究  

Research for Target Tracking Algorithm Based on Extended Kalman Filter

作　　者：蒋婷婷[1] 周洁静 Jiang Tingting;Zhou Jiejing(The 28th Research Institute of China Electronics Technology Group Corporation,Nanjing 210007,China)

机构地区：[1]中国电子科技集团公司第28研究所,南京210007

出　　处：《信息化研究》2020年第2期1-5,共5页INFORMATIZATION RESEARCH

摘　　要：标准粒子滤波(PF)算法虽然对线性、非线性、高斯以及非高斯问题都适用,但是粒子滤波本身也存在粒子退化现象、重采样问题、重要性密度函数的选择问题。这些问题如果处理不好,将会直接影响滤波的性能,所以文章提出了扩展卡尔曼粒子滤波算法(PF-EKF),通过仿真结果得出扩展卡尔曼粒子滤波算法(文章算法)优于粒子滤波算法,整体滤波精度高。Although the standard particle filter(PF)algorithm is suitable for linear,nonlinear,Gaussian and non-Gaussian problems,there are particle degradation,resampling and importance density function selection problems in PF.If these problems are not handled well,it will directly affect the performance of the filter,so this paper proposes the extended Kalman particle filter algorithm(PF-EKF).Through the simulation results,the extended Kalman particle filter algorithm(article algorithm)is better than the particle filter algorithm,and the overall filter accuracy is high.

关 键 词：扩展卡尔曼 粒子滤波 粒子退化 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]