多目标无序量测OOSM-GMPHD滤波算法  

Multi-target OOSM-GMPHD filtering algorithm with out-of-sequence measurement

作　　者：赵凯[1] 胡建旺[1] 吉兵[1] 刘钢[2] 

机构地区：[1]军械工程学院信息工程系 [2]71697部队

出　　处：《传感器与微系统》2017年第11期154-157,160,共5页Transducer and Microsystem Technologies

摘　　要：针对无序量测条件下多目标跟踪问题,提出了一种适用于线性系统的单步滞后无序量测滤波算法(OOSM-GMPHD)。在前向预测框架内,以高斯混合概率假设密度(GMPHD)滤波器为基础滤波算法,对每一高斯分量分别用延迟到达的量测与等价量测进行预测、更新,经剪枝与合并等步骤获得最终的目标数量与状态估计。仿真结果表明:算法可有效消除无序量测的影响,准确估计多目标数目和状态。For addressing multi-target tracking problem with out-of-sequence measurement（ OOSM）,a filtering algorithm is proposed with multiple single-step-lag OOSM for linear system,which denotes as OOSM-Gaussian mixture probability hypothesis density（ GMPHD）. Within the forward prediction framework,taking GMPHD as basis filtering algorithm,predicting and updating each Gaussian component,and then can obtained the target number and state estimation after pruning and merging. etc. Simulation results show that the algorithm can effectively filter out influence of OOSM and can accurately estimate the multi-target number and state.

关 键 词：多目标跟踪 无序量测 单步滞后 高斯混合 前向预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]