基于损失融合策略的长时域中断航迹关联  

Long time domain interrupted track correlation based on loss fusion strategy

作　　者：原鹏飞[1] 吉琳娜[1] 杨风暴[1] Yuan Pengfei;Ji Linna;Yang Fengbao(School of Information and Communication Engineering,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学信息与通信工程学院,太原030051

出　　处：《国外电子测量技术》2023年第11期57-64,共8页Foreign Electronic Measurement Technology

摘　　要：针对目标中断航迹关联存在泛化能力差,长时域中断时关联正确率较低的问题,提出了基于损失融合策略的长时域中断航迹关联方法。首先通过航迹预测将历史航迹预测到与新航迹时域重叠的时刻,计算航迹间平均距离,构造距离损失矩阵,同时计算中断前后航迹的特征参数差值构造特征参数损失矩阵;然后将两类损失融合,构造整体关联代价矩阵;最后通过匈牙利算法实现中断航迹关联决策。将所提方法与距离损失关联方法、特征参数损失关联方法进行实验对比,结果表明,所提方法在不同的场景下关联正确率最高,且对中断时间的适应能力更强,在目标运动状态稳定的场景下平均关联正确率达到90.9%,中断时间小于90 min时,关联正确率优于86%。To address the problems of poor generalization ability of target interrupted track association and low correct rate in long time domain interruption,a long time domain interrupted track association method based on loss fusion strategy is proposed.Firstly,the historical trajectory is predicted to the time domain overlap with the new trajectory through trajectory prediction,and the average distance between trajectories is calculated to construct the distance loss matrix,while the characteristic parameter difference of the trajectory before and after the interruption is calculated to construct the characteristic parameter loss matrix;then,the two types of losses are fused to construct the overall association cost matrix;finally,the interrupted trajectory association decision is realized by the Hungarian algorithm.The experimental comparison of the method proposed in this paper with the distance loss correlation method and the feature parameter loss correlation method shows that the method proposed in this paper has the highest correlation correct rate in different scenarios,and it is more adaptable to the interruption time,with an average correlation correct rate of 90.9%in scenarios where the target's motion state is stable,and the correlation correct rate is better than 86%when the interruption time is less than 90 min.

关 键 词：中断航迹关联 航迹预测 损失融合 匈牙利算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]