关于目标跟踪定位的仿真方法研究

摘要

A Target tracking algorithm is proposed to overcome the defects of poor filtering precision and filtering disconvergence while using unscented Kalman filter. The method combines the advantages of Unscented Kalman Filter (UKF) and adaptive neuro- fuzzy inference system (ANFIS). ANFIS is used to adjust system noise covariance matrix in target tracking system. Fuzzy inference, neural networks and UKF are integrated effectively. The proposed method is applied to simulation of radar target tracking. The simulation results show that the proposed method has the advantages of higher precision, faster convergence, and stronger ability to track maneuvering targets.%研究雷达定位精度和准确性问题,为了解决在目标定位跟踪中由于目标机动引起的无迹卡尔曼滤波(UKF)误差大和滤波发散问题,提出了一种基于UKF和自适应神经网络-模糊推理系统(ANFIS)的新的目标跟踪定位方法.将自适应神经网络-模糊推理系统应用于目标跟踪系统,利用状态变量的预测误差和预测误差的变化率来自适应地调整卡尔曼滤波器的系统噪声协方差矩阵,实现了模糊推理、神经网络和UKF的有效结合,并应用于雷达目标定位跟踪系统进行仿真.仿真结果表明,方法比UKF有更好的跟踪性能,收敛快,对目标机动有更好的适应能力,为设计提供了依据.