基于改进“当前”统计模型的机动目标IMM跟踪算法

交互式多模型(IMM)算法是一种有效的机动目标跟踪算法,但其性能与模型的选择、个数以及参数有关。文中提出了一种基于改进的“当前”统计模型的交互式多模型算法,改进的“当前”统计模型提高了对机动目标的跟踪能力,而常速模型对匀速目标跟踪性能良好,IMM算法通过两种模型的交互作用可以实现对目标状态的自适应估计;同时,该算法结合了模型概率转移自适应技术,实现了对模型转移矩阵的在线估计,降低了人为因素。最后,通过Monte Carlo仿真进一步验证了该算法的有效性。

Maneuvering Target IMM Algorithm Based on Improved Current Statistical Model

The interacting multiple model (IMM) algorithm is an effective solution to maneuvering target tracking. However, its performance depends on the type, number, and parameters of the models. An interacting multiple model algorithm is proposed, which is based on the improved current statistical model. The improved current stat istical model can improve the capacity for tracking maneuvering target, and the constant velocity model has a good performance on tracking constant speed target, so the IMM algorithm can adaptively estimate the state of the target by using the two models. Moreover, with the adaptive Markov transition probability technique, the transition matrix can be modified in real time according to the measurements, which reduces the influence of human factors. Finally, Monte Carlo simulation results show the effectiveness of the proposed algorithm.