HyperTracking

Author:

Xu Xiaoqiang1ORCID,Meng Xuanqi2ORCID,Tong Xinyu1ORCID,Liu Xiulong1ORCID,Xie Xin1ORCID,Qu Wenyu1ORCID

Affiliation:

1. Tianjin University, College of Intelligence and Computing, Tianjin, China

2. Tianjin University, Tianjin, China

Abstract

Wireless sensing technology allows for non-intrusive sensing without the need for physical sensors worn by the target, enabling a wide range of applications, such as indoor tracking, and activity identification. To theoretically reveal the fundamental principles of wireless sensing, the Fresnel zone model has been introduced in the field of Wi-Fi sensing. While the Fresnel zone model is effective in explaining the sensing mechanism in line-of-sight (LoS) scenarios, achieving accurate sensing in non-line-of-sight (NLoS) situations continues to pose a significant challenge. In this paper, we propose a novel theoretical model called the Hyperbolic zone to reveal the fundamental sensing mechanism in NLoS scenarios. The main principle is to eliminate the complex NLoS path shared among different transmitter-receiver pairs, which allows us to obtain a series of simple "virtual" reflection paths among receivers. Since these "virtual" reflection paths satisfy the properties of the hyperbola, we propose the hyperbolic tracking model. Based on the proposed model, we implement the HyperTracking system using commercial Wi-Fi devices. The experimental results show that the proposed hyperbolic model is suitable for accurate tracking in both LoS and NLoS scenarios. We can reduce 0.36 m tracking error in contrast to the Fresnel zone model in NLoS scenarios. When we utilize the proposed hyperbolic model to train a typical LSTM neural network, we are able to further reduce the tracking error by 0.13 m and save the execution time by 281% with the same data. As a whole, our method can reduce the tracking error by 54% in NLoS scenarios compared with the Fresnel zone model.

Funder

National Natural Science Foundation of China

National Key Research and Development Program of China

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture,Human-Computer Interaction

Reference57 articles.

1. Fadel Adib, Zachary Kabelac, and Dina Katabi. 2015. Multi-person localization via {RF} body reflections. In 12th {USENIX} Symposium on Networked Systems Design and Implementation ({NSDI} 15). 279--292.

2. Fadel Adib, Zach Kabelac, Dina Katabi, and Robert C Miller. 2014. 3D tracking via body radio reflections. In 11th {USENIX} Symposium on Networked Systems Design and Implementation ({NSDI} 14). 317--329.

3. See through walls with WiFi!

4. Non-Line of Sight LoRa--Based Localization using RSSI-Kalman-Filter and Trilateration;Anugrah Thirafi Wian;International Journal on Information and Communication Technology (IJoICT),2020

5. Fast and Efficient Cross Band Channel Prediction Using Machine Learning

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3