基于QMCPF-IMM的强机动目标跟踪算法研究

为了提高雷达对机动目标的跟踪精度，通过融合拟蒙特卡罗思想，提出了一种适用于非线性非高斯系统的拟蒙特卡罗粒子滤波交互式多模型算法。该算法利用拟蒙特卡罗采样，克服传统算法采样粒子间隙过大、粒子层叠问题，增加交互式多模型对机动目标跟踪时的有效粒子数；通过区间估计理论，解决拟蒙特卡罗支撑区间难以计算问题，并结合核密度估计重采样，保证采样粒子的低等差异性。仿真结果表明：与交互式多模粒子滤波算法相比，改进算法可在保证滤波实时性的同时，提高跟踪精度。

Tacking of High Maneuvering Target Based in QMCPE-IMM Algorithm

To improve the accuracy of maneuvering target tracking in the nonlinear and non Gaussian systems, an interacting multi-model algorithm based on quasi-Monte Carlo(QMC) particle filter is proposed. The evenly distributed and smaller deviational sample sequence is generated by the QMC sample sequence, which can overcome the traditional Monte Carlo sampling particle''s large gap and stacked problem, increase the effective particles number and improve the particle collection speed. The computational problem of support range in QMC is solved by using interval estimation theory. Simulations show that the improved algorithm can ensure the real-time filter, and improve the tracking accuracy at the same time.