Related Experiment Video
Updated: Jul 12, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
3.8K
A Low-Complexity Hand Gesture Recognition Framework via Dual mmWave FMCW Radar System
Yinzhe Mao1, Lou Zhao1, Chunshan Liu1
1School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China.
Sensors (Basel, Switzerland)
|October 28, 2023
Summary
This study introduces a new, efficient hand gesture recognition system using multiple Frequency Modulation Continuous Wave (FMCW) radars. The framework achieves high accuracy (98.0%) and demonstrates robustness in diverse environments.
Area of Science:
- Engineering
- Computer Science
- Signal Processing
Background:
- Hand gesture recognition is crucial for human-computer interaction.
- Existing methods often face limitations in accuracy and robustness.
Purpose of the Study:
- To propose a novel, low-complexity hand gesture recognition framework.
- To enhance accuracy and robustness using a multi-radar sensing system.
Main Methods:
- Utilizing a distributed system with two Frequency Modulation Continuous Wave (FMCW) radars.
- Employing a neighboring reflection points detection method after 2D-Fast Fourier Transform (2D-FFT).
- Synthesizing motion velocity vectors and applying a long short-term memory (LSTM) network for classification.
Main Results:
- Achieved a high gesture recognition accuracy of 98.0% on a 1600-sample dataset.
- Demonstrated high signal-to-noise ratio (SNR) performance without requiring radar relative position knowledge.
- Validated robustness against environmental background changes and new performers.
Conclusions:
- The proposed multi-FMCW radar system offers an effective and robust solution for hand gesture recognition.
- The combination of synthesized motion vectors and LSTM networks significantly improves recognition accuracy.
- The framework's low complexity and adaptability make it suitable for real-world applications.
