强激光与粒子束, 2005, 17 (9): 1328, 网络出版: 2021-01-27
机动目标跟踪的自适应相互作用多模型算法
Interacting multiple model algorithm in target tracking
机动目标跟踪 相互作用多模型 马尔可夫链 卡尔曼滤波器 Maneuvering targets tracking Interacting multiple model Markovian chain Kalman filter
摘要
针对目标跟踪中的目标机动问题提出了一种"基于自适应相互作用多模型"的算法.使用不同的几个子模型来描述目标的运动状态,各个模型有自己的随目标估计状态和当前测量值变化的模型概率,并且各模型之间能通过马尔可夫链的控制自动平滑切换.仿真实验表明了该算法能很好地适应目标的机动,即使采用两个子模型来描述目标的运动,跟踪精度也比较好.
Abstract
In order to resolve the maneuvering problem in target tracking,an algorithm based on interacting multiple model(IMM) method was presented.In this method every sub-model has its own model match probability that changes with the target's estimated state and measures.The sub-model can soft-jump between each other under the control of Markovian switching coefficients.From simulation it can be seen that the IMM method can improve the tracking accuracy of maneuvering targets.
郑黎义, 潘旭东, 陈兴无, 宋海峰. 机动目标跟踪的自适应相互作用多模型算法[J]. 强激光与粒子束, 2005, 17(9): 1328. ZHENG Li-yi, PAN Xu-dong, CHEN Xing-wu, SONG Hai-feng. Interacting multiple model algorithm in target tracking[J]. High Power Laser and Particle Beams, 2005, 17(9): 1328.