一种双门限自适应多模多目标跟踪算法  

An Adaptive Double Threshold Algorithm for Multi-Target Tracking Based on Interactive Multimode Filter

作　　者：王雪飞[1] 尚朝轩[1] 王昌盛[1] 

机构地区：[1]军械工程学院,石家庄050003

出　　处：《火力与指挥控制》2014年第10期158-162,共5页Fire Control & Command Control

摘　　要：针对机动目标的交互多模跟踪滤波器,提出了基于模型过程噪声自适应调整的双门限的AIMM算法,并对其性能进行了研究,该算法对模型初始参数不敏感,具有稳定性,在目标模型与目标实际运动偏差较大的情况下,具有较好的跟踪性能;针对密集杂波和多目标情况下的目标跟踪,将多模交互滤波的模型自适应调整算法与JPDA算法结合,提出了AIMMJPDA算法的思想与实现。仿真结果显示该方法在机动目标跟踪方面具有模型调整简单、跟踪实时性良好的效果。Aiming at the interactive multimode （IMM）filter for maneuvering targets tracking,an algorithm which utilizes double threshold to adjust model process noise adaptively is proposed,and the JPDA algorithm is combined with the adaptive interactive multimode algorithm to realize target tracking in the cases of dense clutter and multiple targets. The algorithm is not sensitive to initial parameters and can track targets stably. The simulation results show that the method is simple in adjustment of state models of maneuvering target,which has good tracking performance and real-time effect.

关 键 词：交互多模 联合概率数据互联 目标跟踪 双门限 

分 类 号：TN957.51[电子电信—信号与信息处理]