Hand-Gesture Recognition Using Two-Antenna Doppler Radar With Deep Convolutional Neural Networks

Skaria, S, Hourani, A, Lech, M and Evans, R 2019, 'Hand-Gesture Recognition Using Two-Antenna Doppler Radar With Deep Convolutional Neural Networks', IEEE Sensors, vol. 19, no. 8, pp. 3041-3048.


Document type: Journal Article
Collection: Journal Articles

Title Hand-Gesture Recognition Using Two-Antenna Doppler Radar With Deep Convolutional Neural Networks
Author(s) Skaria, S
Hourani, A
Lech, M
Evans, R
Year 2019
Journal name IEEE Sensors
Volume number 19
Issue number 8
Start page 3041
End page 3048
Total pages 8
Publisher IEEE
Abstract Low-cost consumer radar integrated circuits combined with recent advances in machine learning have opened up a range of new possibilities in smart sensing. In this paper, we use a miniature radar sensor to capture Doppler signatures of 14 different hand gestures and train a deep convolutional neural network (DCNN) to classify these captured gestures. We utilize two receiving antennas of a continuous-wave Doppler radar capable of producing the in-phase and quadrature components of the beat signals. We map these two beat signals into three input channels of a DCNN as two spectrograms and an angle of arrival matrix. The classification results of the proposed architecture show a gesture classification accuracy exceeding 95% and a very low confusion between different gestures. This is almost 10% improvement over the single-channel Doppler methods reported in the literature.
Subject Electrical and Electronic Engineering not elsewhere classified
Keyword(s) Radar sensors
deep convolutional neural networks
radar signal processing
hand-gesture recognition
Doppler radar
multi-antenna radar
millimeter-wave radar
DOI - identifier 10.1109/JSEN.2019.2892073
Copyright notice © 2019 IEEE
ISSN 1558-1748
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 14 Abstract Views  -  Detailed Statistics
Created: Mon, 29 Apr 2019, 13:04:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us