A Convolutional Neural Network for Human Motion Recognition and Classification Using a Millimeter-Wave Doppler Radar

• Published in: IEEE sensors journal 2022-03, Vol.22 (5), p.4494-4502
• Main Authors: Arab, Homa, Ghaffari, Iman, Chioukh, Lydia, Tatu, Serioja Ovidiu, Dufour, Steven
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial intelligence; Artificial neural networks; Biometrics; Classification; Continuous wavelet transform; Continuous wavelet transforms; Convolutional neural networks; convolutional neural networks (CNNs); Deep learning; Doppler frequency; Doppler radar; feature extraction; Human motion; in-phase/quadrature demodulator; Machine learning; Microwave amplifiers; Millimeter waves; millimeter-wave; Motion perception; multi-channel CNNs; Neural networks; Noise reduction; Quadratures; Radar; Radar antennas; Radar applications; Radar detection; radar signal processing; Recognition; Reliability analysis; Robotics; sensor; Sensors; Signal classification; Spectrograms; System effectiveness; Two dimensional models; wavelet scalogram; Wavelet transforms
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2022.3140787

Human movement detection based on millimeter-wave radar sensors is a technology of interest in various areas such as for smart surveillance, security, behavioral biometrics, biomedical systems, robotics, etc. This paper shows the feasibility and effectiveness of using a compact 24 GHz Doppler radar with a built-in low-noise microwave amplifier (LNA) for detecting and extracting signals coming from human motion. Reliability and accuracy is assessed based on a comprehensive theoretical analysis, and on simulation results followed by experimental investigations. A continuous wavelet transform (CWT) is used to decompose in-phase and quadrature ( {I/Q} ) baseband signals to extract information about the dynamics of the system. The dataset consists of 1000 recordings in 8 motion classes (standing, walking, sitting, etc.). We propose to apply a two-channel convolutional neural network (CNN), which is composed of two CNN channels, for learning high-level features from time-domain signals and CWT spectrograms. One channel has four one-dimensional (1D) convolutional and pooling layers, and the other channel is made of three two-dimensional (2D) convolutional and pooling layers. In addition, the {I/Q} signals are denoised by using Savitzky-Golay filtering, and both noisy and denoised signals are used as input signals for deep learning data augmentation purpose. We achieved an overall classification accuracy rate of 98.85% in motion classification for a two-branch CNN architecture, and an accuracy rate of 95.3% for a one-branch 2D-CNN. Our results show that a dual-channel CNN model can greatly increase the classification capabilities of human motion recognition and classification, and the proposed method can be effectively used with various radar signal classifications.