Multi-Static UWB Radar-based Passive Human Tracking Using COTS Devices

TL;DR

This paper presents a passive human tracking system using commercial UWB devices, leveraging CNNs and particle filters to achieve high accuracy in indoor environments without active localization.

Contribution

It introduces a novel approach combining CIR and variance-based CNN models with particle filtering for passive human tracking using COTS UWB devices.

Findings

Achieves less than 30 cm RMSE in tracking accuracy.

Variance-based CNN model is robust to scenario changes.

Effective for practical indoor human tracking applications.

Abstract

Due to its high delay resolution, the ultra-wideband (UWB) technique has been widely adopted for fine-grained indoor localization. Instead of active positioning, UWB radar-based passive human tracking is explored using commercial off-the-shelf (COTS) devices. To extract the time-of-flight (ToF) reflected by the moving person, the accumulated channel impulse responses (CIR) and the corresponding variances are used to train the convolutional neural networks (CNN) model. Particle filter algorithm is adopted to track the moving person based on the extracted ToFs of all pairs of links. Experimental results show that the proposed CIR- and variance-based CNN models achieve less than 30-cm root-mean-square errors (RMSEs). Especially, the variance-based CNN model is robust to the scenario changing and promising for practical applications.