Gesture Recognition in Millimeter-Wave Radar Based on Spatio-Temporal Feature Sequences

TL;DR

This paper presents a highly accurate gesture recognition method using millimeter-wave radar signals processed through advanced signal preprocessing and a CNN-TCN model, achieving over 98% accuracy and demonstrating robustness across different neural networks.

Contribution

The paper introduces a novel approach combining mmWave radar signal preprocessing with a CNN-TCN model for robust gesture recognition, achieving high accuracy and generalization.

Findings

Achieves 98.2% recognition accuracy.

Maintains high performance across various neural networks.

Demonstrates robustness and high recognition rate.

Abstract

Gesture recognition is a pivotal technology in the realm of intelligent education, and millimeter-wave (mmWave) signals possess advantages such as high resolution and strong penetration capability. This paper introduces a highly accurate and robust gesture recognition method using mmWave radar. The method involves capturing the raw signals of hand movements with the mmWave radar module and preprocessing the received radar signals, including Fourier transformation, distance compression, Doppler processing, and noise reduction through moving target indication (MTI). The preprocessed signals are then fed into the Convolutional Neural Network-Time Domain Convolutional Network (CNN-TCN) model to extract spatio-temporal features, with recognition performance evaluated through classification. Experimental results demonstrate that this method achieves an accuracy rate of 98.2% in domain-specific recognition and maintains a consistently high recognition rate across different neural networks, showcasing exceptional recognition performance and robustness.