修正的当前统计模型及自适应跟踪算法

A Modified Current Statistical Model and Adaptive Tracking Algorithm

针对当前统计模型及其自适应算法对弱机动目标跟踪精度较低以及强机动发生时刻跟踪误差增大的缺陷，提出了一种修正的当前统计模型及自适应跟踪算法。一方面，利用指数函数对当前统计模型中加速度极值进行实时修正，从而提高了算法对弱机动目标的跟踪精度；另一方面，利用滤波残差调整预测协方差，同时对滤波结果发生较大偏差的上一时刻的滤波结果进行修正，从而提高了对强机动目标的适应能力。仿真结果表明，所提算法对弱机动目标和强机动目标都具有良好的跟踪性能。

The current statistical model （CSM） suffers both low tracking accuracy for weak maneuvering and big tracking error when strong maneuvering happens. A modified current statistical model （ MCSM ） and adaptive tracking algorithm is proposed to deal with these problems. On the one hand, an exponential function is designed to adjust the maximum acceleration so as to im- prove the tracking accuracy for weak maneuvering. On the other hand, to lower the tracking error in case of strong maneuvering, the filtering residual is used to adjust the covariance prediction, and the filtering result at the last time is to be modified if the inno- vation is bigger than a preset threshold. Simulation results show that the proposed algorithm performs well in both cases of weak maneuvering and strong maneuvering.