快速边缘粒子滤波在无序量测问题中的应用

Application of FMPF in OOSM problem

在目标跟踪系统中,因通信延迟会出现传感器量测无序到达融合中心的现象,由此产生无序量测(OOSM)融合问题。针对非线性条件下的OOSM问题,在现有算法的基础上,提出了基于快速边缘粒子滤波(FMPF)的处理算法。新算法在FMPF框架下,结合前向预测滤波思想来处理OOSM问题。将目标运动状态向量分为线性和非线性2个子向量,并分别采用相应的无序处理算法进行估计。算法可以处理单步延迟和多步延迟的情形下的无序问题。最后理论分析和仿真实验表明:新算法能有效处理OOSM问题,且降低了算法的计算复杂度,提高了算法实时性。

In target tracking system, sensor measurements may arrive at the fusion center out of sequence because of the different communication delays, which results in the out-of-sequence measurement（OOSM） problem. Aiming at the OOSM problem in nonlinear condition, based on fast marginalized particle filtering （FMPF）solution algorithm is proposed on the basis of existing algorithm. The new algorithm deals with OOSM by combing the framework of FMPF and the idea of forward prediction filtering. The state vector of target motion is divided into linear state sub-vector and nonlinear state sut-veetor, and correspondin~ OOSM algorithm are used to estimate. The algorithm can deal with OOSM problem both in 1-step-lag and multi-step-lags case. Theoretical analysis and simulation experiment indicates that the new algorithm can effectively deal with OOSM problem and reduces computation complexity and increase real-time of the algorithm.