WiImg: Pushing the Limit of WiFi Sensing with Low Transmission Rates

WiFi has achieved great success in data communication in the past two decades and WiFi signals are recently further exploited for sensing purposes. Promising progress has been achieved and diverse WiFi sensing applications have been enabled. However, one critical issue which was not paid much attention to and we believe would greatly hinder the real-life adoption of WiFi sensing is that it actually affects WiFi communication. The fundamental reason is that WiFi sensing requires high-frequency signal samples and WiFi data packets can not meet this requirement. Therefore, existing WiFi sensing systems transmit dedicated high-frequency packets (200-2000 packets per second) for sensing and these “sensing packets” greatly affect the main data communication function of WiFi. In this work, we propose WiImg, a lightweight system which involves machine learning techniques to enable WiFi sensing under low packet rate, pushing WiFi sensing one step towards real-life adoption. The key idea is to convert the CSI samples into images and improve the Generative Adversarial Network (GAN) for CSI image inpainting, relaxing the requirement of high sample rate in sensing. To avoid the large training overhead of GAN, we design a lightweight GAN that leverages samples of only three rates to recover the CSI traces of any arbitrary rates. Experiments show that with just 25 packets per second, WiImg is able to increase the recognition accuracy for hand gesture recognition and daily activity tracking from the state-of-the-art 59.1% and 65.9% to 86.7% and 96.4%, respectively.

I. Introduction

Wireless technologies have changed the way we work and live. Among them, WiFi is one of the most important wireless technologies and WiFi infrastructure has been pervasively deployed in indoor environments for Internet connections. In the last few years, a lot of research attempts further exploited WiFi signals for sensing purposes [1]–[5]. The basic principle is that WiFi signals vary with changes in the environment. If a human target moves in the area covered by WiFi, the WiFi signal reflected from the target changes with human movements. Therefore, by analyzing the signal variation induced by the target, we can obtain the target movement information without requiring any sensors. The sensor-free and contact-free nature of WiFi sensing is very appealing and WiFi sensing has been applied to realize a wide range of applications including passive localization [6]–[8], activity recognition [9]–[11], identity authentication [12]–[14] and even vital sign monitoring [15]–[17].