摘要
在研究多传感器的目标跟踪数据融合时,针对算法都需要事先了解数据的一部分先验知识,虽然能够提高数据的跟踪精度,但只能应用到事后的数据分析中。为了使融合中心能在传感器录取目标数据的同时进行跟踪数据的融合处理,数据融合算法必须实现实时性。为了解决数据融合算法在提高精度的同时不需要以先验知识为背景的问题,提出一种利用数据间支持度函数矩阵进行多组数据加权融合的结果来替代滤波测量值进行卡尔曼滤波,并得到多组测量数据的实时动态融合跟踪。仿真结果表明,能够实时跟踪目标,同时数据融合的跟踪精度大大提高。
Most data fusion arithmetic needs some advance knowledge when doing the target tracking data fusion.Although it can improve the tracking precision,it can only be applied in data disposal afterwards.For the fusion center demands record data and deals with the data at the same time,it should consider the simultaneous factor of the data fusion method.Aimed to solve the problem of improving data fusion precision without the advance knowledge simultaneously,one method is put forward,which uses the result of weighting fusion by calculating the function of supporting degree among data to replace the input measured data of the filter and carry on kalman filtering.Then the realtime dynamic data fusion tracking of multiple group data is obtained.The result of simulation shows that this method can acquire more accurate fusion data.
出处
《计算机仿真》
CSCD
北大核心
2010年第11期44-47,共4页
Computer Simulation
关键词
数据融合
数据间支持度矩阵
卡尔曼滤波
目标跟踪
Data fusion
Function of supporting degree among data
Kalman filtering
Target tracking