IMM迭代无迹Kalman粒子滤波目标跟踪算法

IMM iterated unscented Kalman particle filter algorithm for target tracking

针对传统交互式多模型(interactive multiple model,IMM)算法跟踪机动式再入目标精度差和实时性不高的问题,提出一种交互式多模型迭代无迹Kalman粒子滤波算法。该算法在多模型滤波过程中采用改进的粒子滤波算法,通过迭代无迹Kalman滤波融入最新观测信息,进而生成粒子滤波的重要性密度分布,从而提高采样质量,改善滤波算法性能。仿真结果表明,提出的算法相对于交互式多模型粒子滤波算法具有更好的跟踪效果。该算法对提高跟踪机动式再入目标的精度与实时能力具有一定的理论意义。

In view of the poor performance of traditional interactive multiple model（ IMM） algorithm for tracking maneuvering reentry target,an interactive multiple model iterated unscented Kalman filter algorithm is put forward. The algorithm uses the improved particle filter in the filtering process of multi-model and generates the importance density distribution of particle filter by using iterated unscented Kalman filter,which improves sampling quality and performance. Simulation results show that the proposed algorithm compared to the interactive multiple model particle filter algorithm has better tracking performance.