一种目标特性辅助的积分粒子滤波新方法

A Novel Auxiliary Quadrature Particle Filtering Algorithm Based on Target Characteristic

针对非均匀稀疏采样环境下目标跟踪中的非线性滤波问题,提出了一种基于Gauss-Hermite积分和目标特性辅助的积分粒子滤波新方法(AQPF).在该方法中,构建了基于Gauss-Hermite积分的积分点概率密度函数作为重要性密度函数,同时,在时间更新阶段引入目标观测、目标观测的有效时间间隔、目标速度等目标特性,综合改善滤波器中预测粒子和预测协方差估计的准确性和粒子的多样性,有效提高目标状态的估计性能.实验结果表明,提出方法的估计性能要明显好于无迹kalman滤波(UKF)、积分kalman滤波(QKF)、粒子滤波(PF)、辅助粒子滤波(APF)和高斯粒子滤波(GPF),能够有效对目标状态进行估计.

For the nonlinear filtering problem of target tracking in aperiodic sparseness sampling environment,a novel auxiliary quadrature particle filter（ AQPF） based on Gauss-Hermite quadrature and target characteristics is proposed.In the proposed algorithm,a set of quadrature point probability densities based on the Gauss-Hermite quadrature is proposed to approximate the important density function.At the same time,the proposed algorithm can incorporate target observation,time interval of the target observation and the target speed into the construction of important density function,which can effectively enhance the diversity of samples and improve the performance.Finally,the experimental results show that the performance of the proposed algorithm is better than these of the unscented Kalman filter（ UKF）,quadrature Kalman filter（ QKF）,particle filter（ PF）,auxiliary particle filtering（ APF） and Gaussian particle filter（ GPF）,and can effectively estimate the target states.