WiRiS: Transformer for RIS-Assisted Device-Free Sensing for Joint People Counting and Localization using Wi-Fi CSI
Abstract
Channel State Information (CSI) is widely adopted as a feature for indoor localization. Taking advantage of the abundant information from the CSI, people can be accurately sensed even without equipped devices. However, the positioning error increases severely in non-line-of-sight (NLoS) regions. Reconfigurable intelligent surface (RIS) has been introduced to improve signal coverage in NLoS areas, which can re-direct and enhance reflective signals with massive meta-material elements. In this paper, we have proposed a Transformer-based RIS-assisted device-free sensing for joint people counting and localization (WiRiS) system to precisely predict the number of people and their corresponding locations through configuring RIS. A series of predefined RIS beams is employed to create inputs of fingerprinting CSI features as sequence-to-sequence learning database for Transformer. We have evaluated the performance of proposed WiRiS system in both ray-tracing simulators and experiments. Both simulation and real-world experiments demonstrate that people counting accuracy exceeds 90\%, and the localization error can achieve the centimeter-level, which outperforms the existing benchmarks without employment of RIS.
Cite
@article{arxiv.2304.06475,
title = {WiRiS: Transformer for RIS-Assisted Device-Free Sensing for Joint People Counting and Localization using Wi-Fi CSI},
author = {Wei-Yu Chung and Li-Hsiang Shen and Kai-Ten Feng and Yuan-Chun Lin and Shih-Cheng Lin and Sheng-Fuh Chang},
journal= {arXiv preprint arXiv:2304.06475},
year = {2023}
}