王妙羽1,,,
丁昊1, 2,
李成华1, 2
1.中南民族大学电子信息工程学院 武汉 430074
2.湖北省智能无线通信重点实验室 武汉 430074
基金项目:国家自然科学基金(61402544)，中南民族大学中央高校专项(CZQ14001)，湖北省自然科学基金(2017CFB874)，中央高校基本科研业务费专项(CZY17001)
详细信息
作者简介:江小平：男，1974年生，副教授，研究方向为信号与信息处理
王妙羽：女，1994年生，硕士生，研究方向为通信与信息系统
丁昊：男，1980年生，讲师，研究方向为图像信号处理，神经网络和压缩感知
李成华：男，1972年生，副教授，研究方向为计算机应用
通讯作者:王妙羽 2016110191@mail.scuec.edu.cn
中图分类号:TN911.7计量
文章访问数:1524
HTML全文浏览量:624
PDF下载量:57
被引次数:0
出版历程
收稿日期:2018-09-06
修回日期:2019-09-25
网络出版日期:2020-01-11
刊出日期:2020-06-04
Passive Fingerprint Indoor Positioning Based on CSI Amplitude-phase
Xiaoping JIANG1, 2,Miaoyu WANG1,,,
Hao DING1, 2,
Chenghua LI1, 2
1. School of Electronic Engineering, South-central University for Nationalities, Wuhan 430074, China
2. Hubei Province Key Laboratory of Intelligent Wireless Communication, Wuhan 430074, China
Funds:The Natural Science Foundation of China (61402544), Central South University for Nationalities of China Central University Special Project (CZQ14001), The Nature Science Foundation of Huibei Province (2017CFB874), The Fundamental Research Funds for the Central University (CYZ17001)
摘要
摘要:基于信道状态信息(CSI)的室内定位技术近几年备受关注。已提出的室内定位方案主要在适用性和定位精度等方面进行不断地创新和改进。该文提出一种被动式的1发2收指纹室内定位系统。用两个固定接收端采集CSI数据，信号预处理阶段对CSI幅值进行奇异值去除与低通滤波，用线性拟合的方法对CSI相位进行校正，将两个接收端采集处理得到的CSI幅值和相位信息共同作为指纹，最终通过全连接神经网络对指纹样本进行训练，并与采集到的实时数据进行匹配识别。实验表明，采用两个接收端以及幅值和相位结合定位的方法，匹配识别率达到了98%，定位精度达到0.69 m。证明该系统能精确有效地实现室内定位。
关键词:室内定位/
信道状态信息/
幅值-相位指纹/
神经网络
Abstract:Indoor positioning technology based on Channel State Information (CSI) receives much attention in recent years. The existing indoor positioning solution is continuously innovative and improved in terms of deployment implementation and positioning accuracy. This paper proposes a passive one-transmitter two-receivers fingerprint indoor positioning system. The CSI data is collected by two fixed receiving end-devices. In the signal preprocessing stage, the CSI amplitude is singular value removed and low pass filtered, and the CSI phase is corrected by a linear fitting method, and the CSI amplitude and phase information obtained by the two receiving ends are collectively used as fingerprint samples. The fingerprint samples are finally trained through the fully connected neural network, and matched with the collected real-time data. Experiments show that the matching recognition rate reaches 98% by using two receivers and the combination of amplitude and phase positioning, and the positioning accuracy is 0.69 m. It proves that the system can accurately and effectively achieve indoor positioning.
Key words:Indoor location/
Channel State Information (CSI)/
Amplitude-phase fingerprint/
Neural networks
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=10aba411-9612-41e1-bfb4-dd2e28654615
