Pulsed Millimeter Wave Radar for Hand Gesture Sensing and Classification

A pulsed millimeter wave radar operating at a frame rate of 144 Hz is utilized to record 2160 scattering signatures of 12 generic hand gestures. Gesture recognition is achieved by machine learning, utilizing transfer learning on a pretrained convolutional neural network. This yields excellent classi...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE sensors letters Vol. 3; no. 12; pp. 1 - 4
Main Authors:	Fhager, Lars Ohlsson, Heunisch, Sebastian, Dahlberg, Hannes, Evertsson, Anton, Wernersson, Lars-Erik
Format:	Journal Article
Language:	English
Published:	Piscataway IEEE 01-12-2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Artificial intelligence Artificial neural networks Classification Computer and Information Science Computer Vision and Robotics (Autonomous Systems) convolutional neural network Convolutional neural networks Data- och informationsvetenskap (Datateknik) Datorseende och robotik (autonoma system) Gesture recognition gesture sensing hand gesture recognition Machine learning Microwave/millimeter wave sensors Millimeter wave measurements Millimeter wave radar Millimeter waves Natural Sciences Naturvetenskap Neural networks Orthogonality pulsed radar Radar Radar imaging Recognition Sensors transfer learning
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	A pulsed millimeter wave radar operating at a frame rate of 144 Hz is utilized to record 2160 scattering signatures of 12 generic hand gestures. Gesture recognition is achieved by machine learning, utilizing transfer learning on a pretrained convolutional neural network. This yields excellent classification results with a validation accuracy of 99.5%, based on a 60% training versus 40% validation split. The corresponding confusion matrix is also presented, showing a high level of classification orthogonality between the tested gestures. This is the first demonstration where data from a pulsed millimeter wave radar is used for gesture recognition by machine learning. It proves that the range-time envelope representation of high frame-rate data from a pulsed radar is suitable for hand gesture recognition. Further improvements are expected for more complex detection schemes and tailored neural networks.
ISSN:	2475-1472 2475-1472
DOI:	10.1109/LSENS.2019.2953022