摘要
针对非线性机动目标跟踪中滤波器易发散、跟踪精度低等问题,将容积卡尔曼滤波器(CKF)引入到交互式多模型算法(IMM)中,设计了交互式多模型容积卡尔曼滤波算法(IMMCKF)。该算法采用Markov过程描述多个目标模型间的切换,利用CKF滤波器对每个模型进行滤波,将各滤波器状态输出的概率加权融合作为IMMCKF的输出。仿真结果表明,与IMMUKF算法相比,IMMCKF算法跟踪精度更高,模型切换速度更快,计算量更小,该算法具有重要的工程应用价值。
In nonlinear maneuvering target tracking,the tracking filters are liable to diverge and the tracking precision is low.To solve this problem,an Interacting Multiple Model Cubature Kalman Filter（IMMCKF） was designed by introducing CKF into IMM algorithm.This method used Markov process to describe switching probability among the models,and used CKF filter for filtering each model.The weighted sum of the outputs of all parallel CKF was taken as the output of IMMCKF.Simulation shows that IMMCKF has higher precision,quicker model switching speed,and smaller calculation cost compared with IMMUKF.The algorithm is of great engineering application value.
出处
《电光与控制》
北大核心
2011年第10期1-5,共5页
Electronics Optics & Control
基金
武器装备军内科研项目
关键词
机动目标跟踪
交互式多模型
容积卡尔曼滤波
maneuvering target tracking
Interacting Multiple Model（IMM）
cubature Kalman Filter
