摘要
本文提出了一种分散式大规模多目标跟踪网络的传感器选择优化算法.该方法以多目标状态集和估计集间的均方最优子模式分配误差下界作为优化目标函数,根据加权Kullback-Leibler平均(Kullback-Leibler average,KLA)准则对局部多目标密度进行融合,最终采用坐标下降法来折中计算代价和跟踪精度.仿真实验在不同信噪比场景下验证了本方法的有效性.
A sensor selection optimization algorithm is proposed for decentralized large-scale multi-target tracking network.In this method,the lower bound of mean square optimal sub-pattern assignment error between multi-target state set and its estimation is taken as optimized objective function while the rule of weighted Kullback-Leibler average(KLA) is used to fuse local multi-target densities.The coordinate descent method is proposed to compromise the computation cost and tracking accuracy.Simulations verify the effectiveness of our method under different signal-to-noise ratio scenarios.
作者
连峰
张修立
魏博
侯利明
韩崇昭
王伟
LIAN Feng;ZHANG Xiu-li;WEI Bo;HOU Li-ming;HAN Chong-zhao;WANG Wei(School of Electronic and Information Engineering, Xi' an Jiaotong University, Xi' an, Shaanxi 710049 , China;Shaanxi Key Laboratory cf Integrated and Intelligent Navigation ,Xi'an,Shaanxi 710068 ,China;The 20th Research Institute of China Electronics Technology Corporationan,Shaanxi 710068, China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2019年第10期2158-2165,共8页
Acta Electronica Sinica
基金
国家自然科学基金(No.61473217)
陕西省组合与智能导航重点实验室开放基金(No.SKLIIN-20180110)
关键词
传感器选择
多目标跟踪
标签随机有限集
分散式传感器网络
sensor selection
multi-target tracking
labeled random finite set
decentralized sensor network
