Target Tracking Algorithm Using Gaussian Cost-Reference Particle Filter in WSN Based on Multi-Modality Information

作     者：Jian Zhang,Chengdong Wu,Zixi Jia,Tianbao Wang School of Information Science and Engineering,Northeastern University,Shenyang,110004 

会议名称：《2010 Chinese Control and Decision Conference》

会议日期：2010年

学科分类：080904[工学-电磁场与微波技术] 0810[工学-信息与通信工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 080202[工学-机械电子工程] 08[工学] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 081001[工学-通信与信息系统] 

基　　金：supported by National Nature Science Foundation under Grant 60874103 

关 键 词：Wireless Sensor Networks Multi-Modality Target Tracking Gaussian Cost-Reference Particle Filter 

摘      要：正Target tracking algorithm using Gaussian cost-reference particle filter in WSN based on multi-modality information is proposed in this *** with WSN relying on sensors of single modality,two different nodes organize the network;Contrary to traditional particle filter algorithm for target tracking,this algorithm does not assume explicit mathematical models of the noise probabilistic distributions,but approximate posterior probability distribution of the state using Gaussian *** mean and variance of Gaussian distribution as information interacted between nodes only need to be *** results show that the algorithm can satisfy the need of a tracking accuracy and efficiently prolong the network lifetime.