机动目标跟踪中数据互联新方法

A Novel Data Association Method for Maneuvering Target Tracking

为解决机动目标跟踪过程中的数据互联问题,该文提出了一种数据互联新方法。与概率数据互联滤波器不同,在进行数据互联时,该方法假定目标当前转弯率在某一范围内取值,这样其预测中心不再是一个点,而是一线段。在计算测量的权重系数时,采用的是测量距该线段的距离。仿真实验表明,杂波环境下对机动目标跟踪时,该方法降低了航迹丢失率,提高了状态估计的精度。

To solve the problem of data association in maneuvering target tracking, a new method of data association is proposed. Being different from the Probabilistic Data Association Filter （PDAF）, the proposed method assumes that the current turn rate of a maneuvering target changes within a limited range in data association. Therefore, the forecasting center is not a point but a short line. The distance between a measurement and the short line is utilized to compute the weight factor of the measurement. Simulation results show that the proposed method reduces the percentage of lost tracks and improves the state estimating accuracy in tracking a maneuvering target under the circumstance of clutter.