Efficient Convolutional Neural Network for FMCW Radar Based Hand Gesture Recognition

TL;DR

This paper presents a convolutional neural network that effectively recognizes hand gestures using FMCW radar data, demonstrating high accuracy and real-time performance for radar-based human-computer interaction.

Contribution

The study introduces a novel CNN model that combines range, speed, and azimuth data from FMCW radar for accurate gesture recognition.

Findings

Achieved 96% accuracy on test set

Demonstrated real-time recognition capability

Validated robustness of radar-based gesture interface

Abstract

FMCW radar could detect object's range, speed and Angleof-Arrival, advantages are robust to bad weather, good range resolution, and good speed resolution. In this paper, we consider the FMCW radar as a novel interacting interface on laptop. We merge sequences of object's range, speed, azimuth information into single input, then feed to a convolution neural network to learn spatial and temporal patterns. Our model achieved 96% accuracy on test set and real-time test.