基于传递闭包聚类的多传感器航迹关联算法  

Multi Sensor Track Correlation Algorithm Based on Transitive Closure Fuzzy Clustering

作　　者：黄友澎[1,2] 周永丰[2] 李琳[2] 张海波[2] 

机构地区：[1]哈尔滨工程大学计算机科学与技术学院,哈尔滨150001 [2]武汉数字工程研究所,武汉430074

出　　处：《武汉理工大学学报（交通科学与工程版）》2008年第5期834-837,共4页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国防"十一五"预研基金项目(批准号:06J3.9.4);国防"十一五"预研计划项目(批准号:101070301);国防科工委"十一五"预研计划项目(批准号:C0820061362)资助

摘　　要：在分布式多传感器数据融合系统中,航迹关联是关键技术之一,也是实现航迹融合的前提,航迹关联判定的准确性将直接影响到整个融合系统的性能.文中针对多传感器多目标航迹关联问题,提出了基于传递包模糊聚类的多传感器航迹关联算法.该算法利用基于模糊统计量的传递闭包聚类法,选择航迹的位置、速度等信息为聚类指标,对来自多传感器的航迹数据进行聚类,计算航迹相似矩阵,利用平方法求出航迹相似矩阵的传递闭包,并根据该传递闭包确定航迹关联对.仿真试验结果表明,该方法能有效地实现多传感器、多目标航迹关联.Track correlation has been recognized as one of the key technologies in distributed multiple-sensor multiple-target data fusion systems. The correctness of correlation judged would directly impact on the performance of the whole fusion system. This paper presents a multisensor track correlation algorithm based on transitive closure fuzzy clustering. First of all, the data fusion center receives target tracks information from each sensor system, selects clustering indexes and calculates similarity matrix. Then, the transitive closure of similarity matrix is calculated by the square algorithm. Finally, cluster tracks using transitive closure fuzzy clustering algorithm and track correlation pairs is determined. The results of simulation experiment show that this algorithm can effectively accomplish the track correlation.

关 键 词：航迹关联 多传感器 传递闭包 模糊聚类 

分 类 号：TN957[电子电信—信号与信息处理] TP274[电子电信—信息与通信工程]