基于EMD和灰关联技术的航迹关联方法  

Track association approach based on EMD method and gray correlation technique

作　　者：郭文艳[1] 韩崇昭[1] 雷明[1] 

机构地区：[1]西安交通大学电子与信息工程学院

出　　处：《控制与决策》2008年第7期803-807,共5页Control and Decision

基　　金：国家973计划项目(2001CB309403);国家自然科学基金项目(60574033);西安理工大学创新计划项目(108-210602)

摘　　要：针对分布式多传感器融合多目标跟踪系统,提出一种基于经验模态分解(EMD)和灰关联技术的航迹关联方法.首先采用EMD方法将各传感器的航迹信息分解为多个固有模态函数(IMF)之和;然后以各IMF构成矩阵,对其进行奇异值分解;再以奇异值作为各航迹的特征向量,计算特征向量间的灰关联度;最后通过各关联度的融合,得到航迹正确关联的结果.典型情况下的仿真结果表明,与加权法相比,该方法能有效地用于航迹关联.For distributed multi-sensor fusion muli-target tracking system, a track association method based on empirical mode decomposition （EMD） and gray correlation technique is proposed. The EMD method is used to decomposed the track of each sensor into many of intrinsic mode function （IMF） components which form initial matrixes. The si.ngular value, regard as the characteristic vectors of the track of each sensor, is obtained by applying the singular value decomposition technique to the initial matrixes. By fusing the gray＇ correlation between the characteristic vectors, the ture track association rusults are obtained. The simulation results under the typical environment are compared against the weight track association and show the effectiveness of the proposed algorithm.

关 键 词：信息融合 航迹关联 经验模态分解 固有模态函数 奇异值分解 灰关联 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]