基于地磁轨迹信号的新型室内定位  

A Novel Indoor Positioning Based on Geomagnetic Trajectory Signal

作　　者：孙垚棋 巩鹏博 徐浙峰 李文钧[2] 颜成钢 郑博仑 张继勇 SUN Yaoqi;GONG Pengbo;XU Zhefeng;LI Wenjun;YAN Chenggang;ZHENG Bolun;ZHANG Jiyong(School of Automation,Hangzhou Dianzi University,Hangzhou,Zhejiang 310018,China;School of Electronics and Information,Hangzhou Dianzi University,Hangzhou,Zhejiang 310018,China)

机构地区：[1]杭州电子科技大学自动化学院,浙江杭州310018 [2]杭州电子科技大学电子信息学院,浙江杭州310018

出　　处：《信号处理》2021年第6期952-957,共6页Journal of Signal Processing

基　　金：国家自然科学基金资助项目(61931008,61671196,62001146,61971268,61972123);浙江省自然科学基金资助项目(LR17F030006)。

摘　　要：无处不在的地磁场由于室内环境中建筑结构的差异而具有独特的特征。此外,地磁信号的分辨难度会导致定位结果的不准确。本文提出了一种使用深度神经网络来提高定位精度的地磁室内定位系统。为了解决地磁场的低分辨率问题,本文将连续的地磁信号矢量化为轨迹序列,并以此为基础设计了一种新的地图构建方法来搭建用于室内定位的地磁数据库。然后,通过引入时间卷积网络(TCN)来提取磁轨迹序列的深层特征。实验结果表明,这种方法优于KNN和基于LSTM的DRNN等其他机器学习算法。Ubiquitous geomagnetic field exhibits unique features due to differences between building structures in indoor environments.In addition,the difficulty of resolving geomagnetic signals will lead to inaccurate positioning results.This paper proposes a geomagnetic indoor positioning system using deep neural networks to improve positioning accuracy.In order to solve the problem of low discernibility of the geomagnetic filed,continuous geomagnetic signals are vectorized into a trajectory sequence,and a novel map-building method is designed based on this to geomagnetic database for indoor positioning.Then,temporal convolutional network(TCN)is introduced to extract deep features of geomagnetic trajectory sequences.Experimental results show that the method outperforms other machine learning algorithms,such as KNN and LSTM-based DRNN.

关 键 词：地磁场 室内定位 时间卷积神经网络 

分 类 号：TN911.23[电子电信—通信与信息系统]