Gesture Recognition for FMCW Radar on the Edge

This paper introduces a lightweight gesture recognition system based on 60 GHz frequency modulated continuous wave (FMCW) radar. We show that gestures can be characterized efficiently by a set of five features, and propose a slim radar processing algorithm to extract these features. In contrast to p...

Full description

Saved in:
Bibliographic Details
Published inIEEE Topical Conference on Wireless Sensors and Sensor Networks (Online) pp. 45 - 48
Main Authors Strobel, Maximilian, Schoenfeldt, Stephan, Daugalas, Jonas
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.01.2024
Subjects
edge computing
Feature extraction
Gesture recognition
machine learning
Radar
Radar imaging
radar sensing
Recurrent neural networks
Sensors
Wireless sensor networks
Online AccessGet full text
ISSN2473-4624
DOI10.1109/WiSNeT59910.2024.10438579

Cover

More Information
Summary:This paper introduces a lightweight gesture recognition system based on 60 GHz frequency modulated continuous wave (FMCW) radar. We show that gestures can be characterized efficiently by a set of five features, and propose a slim radar processing algorithm to extract these features. In contrast to previous approaches, we avoid heavy 2D processing, i.e. range-Doppler imaging, and perform instead an early target detection - this allows us to port the system to fully embedded platforms with tight constraints on memory, compute and power consumption. A recurrent neural network (RNN) based architecture exploits these features to jointly detect and classify five different gestures. The proposed system recognizes gestures with an F1 score of 98.4% on our hold-out test dataset, it runs on an Arm® Cortex®-M4 microcontroller requiring less than 280 kB of flash memory, 120 kB of RAM, and consuming 75 mW of power.
ISSN:2473-4624
DOI:10.1109/WiSNeT59910.2024.10438579