Light-weight Gesture Sensing Using FMCW Radar Time Series Data

TL;DR

This paper introduces a lightweight, real-time gesture recognition method using FMCW radar data processed directly in the time domain, achieving high accuracy on embedded devices without Fourier transforms.

Contribution

It presents a novel time-domain feature extraction technique for FMCW radar that simplifies processing and enables efficient deep learning-based gesture recognition on low-power hardware.

Findings

Achieves 95% gesture recognition accuracy

Operates in real time on Raspberry Pi 3 B

Reduces computational complexity significantly

Abstract

The paper proposes a novel feature extraction approach for FMCW radar systems in the field of short-range gesture sensing. A light-weight processing is proposed which reduces a series of 3D radar data cubes to four 1D time signals containing information about range, azimuth angle, elevation angle and magnitude. The processing is entirely performed in the time domain without using any Fourier transformation and enables the training of a deep neural network directly on the raw time domain data. It is shown experimentally on real world data, that the proposed processing retains the same expressive power as conventional radar processing to range-, Doppler- and angle-spectrograms. Further, the computational complexity is significantly reduced which makes it perfectly suitable for embedded devices. The system is able to recognize ten different gestures with an accuracy of about 95% and is running in real time on a Raspberry Pi 3 B. The delay between end of gesture and prediction is only 150 ms.