稳健的交互多模型转移概率选择算法

Robust transfer probability selection algorithm in interacting multiple model method

交互多模算法(IMM)是机动目标跟踪中最常使用的方法之一,但其计算量大、过程较复杂。针对交互多模型转移概率矩阵选取问题,结合目标机动检测理论,提出稳健的交互多模型转移概率选择算法。该方法通过判别机动和非机动目标,确定转移概率矩阵主对角线元素值,并进行了仿真实验。结果显示,新方法简便可靠,提高了总体的滤波效果。

Interacting multiple model algorithms, as one of the most useful methods in maneuvering target tracking, suffers very big calculation and more complicated process. Aimed at the selection of transfer matrix in interacting multiple model, this paper introduces robust transfer probability selection method, combined with the maneuvering detection theory in target tracking. Based on the estimation of maneuvering and nonmaneuvering, the method permits the determination of selection of the diagonal elements in the transfer probability matrix. The simulation experiment shows that the new method is simple and reliable and the general filtering effect is improved.