基于迭代平方根容积粒子滤波目标跟踪算法

Target Tracking Algorithm Based on Iterated Square Root Cubature Particle Filter

针对粒子滤波目标跟踪算法粒子退化及跟踪精度问题,提出了一种基于马尔可夫链-蒙特卡罗(MCMC,Markov Chain Monte Carlo)的迭代平方根容积粒子滤波(ISRCPF,iterated square root cubature Kalman particle filter)算法(ISRCPF-MCMC)。在该滤波算法中,利用容积数值积分原则计算非线性随机函数的均值和方差,通过正交矩阵分解代替矩阵开方,在生成的粒子滤波建议分布中融入当前量测值,提高对系统后验概率的逼近程度。然后在此基础上融合MCMC抽样算法(MH,Metropolis Hasting)对所选建议分布进行优化,增加粒子多样性,以提高跟踪精度。仿真试验结果表明,ISRCPF-MCMC算法的估计误差与其他算法相比降低至0.403%。

In order to solve the problems of particle degradation and tracking accuracy in the particle filter target tracking algorithm,a new improved particle filter algorithm called iterated square root cubature Kalman particle filter（ISRCPF） is proposed based on Markov Chain Monte Carlo（MCMC）.The new ISRCPF-MCMC uses the cubature principle of numerical integration to calculate the mean and covariance of nonlinear function.By using orthogonal matrix decomposition instead of matrix prescribing and adding the current measured values into the resulting particle filter proposal distribution to improve the degree of approximation to the system posterior density.After thtat,by together using MCMC sampling method,proposal distribution is optimized,particles be come,and accuracy is improved.Simulation results show that the estimation error of ISRCPF-MCMC algorithm is reduced to 0.403%compared with other algorithms.