基于无线传感网的目标检测算法  

Target detection algorithm based on wireless sensor network

作　　者：王璞瑶 徐淑芳[1] 游旭东 孟朝晖[1] Wang Puyao;Xu Shufang;You Xudong;Meng Zhaohui(Hohai University,Nanjing 211100,China;Xiamen University,Xiamen 361000,China)

机构地区：[1]河海大学,南京211100 [2]厦门大学,厦门361000

出　　处：《电子测量技术》2020年第6期143-147,159,共6页Electronic Measurement Technology

摘　　要：利用无线传感网进行目标检测的实验研究,定义了观测节点层、汇聚节点层和融合信息层三层网络结构。并且基于Counting Rule规则提出了新的信息融合规则--远距点融合规则(DFFR),比较了不同融合规则下检测系统的性能,并绘制了ROC曲线图像。同时,研究了DFFR融合规则下,检测系统中传感器个数、信噪比(SNR)等因素对检测结果的影响。实验结果表明,随着观测节点、SNR的增加,系统的检测性能会越来越好。在实际应用中,可以考虑到成本、使用环境等因素,选取合适的参数,以实现最佳的目标检测性能。In this paper,the experimental study of target detection using wireless sensing network is carried out,and three layers of network structure are defined:observation node layer,sink node layer and fusion information layer.Based on the Counting rule,a new information fusion rule,distance Far Fusion Rule,(DFFR),is proposed to compare the performance of the detection system under different fusion rules,and the ROC curve image is drawn.At the same time,the influence of the number of sensors and signal-to-noise ratio(SNR)on the detection results under DFFR is studied.The experimental results show that the detection performance of the system will be better and better with the increase of SNR of the observation nodes.In practical application,the cost,use environment and other factors can be taken into account,and the appropriate parameters can be selected to achieve the best target detection performance.

关 键 词：无线传感网 目标检测 信息融合 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]