This paper presents a new method for detecting and classifying a predefined set of hand gestures using a single transmitter and a single receiver utilizing a linearly frequency modulated ultrasonic signal. Gestures are identified based on estimated range and received signal strength (RSS) of reflected signal from the hand. Support Vector Machine (SVM) was used for gesture detection and classification. The system was tested using experimental setup and achieved an average accuracy of 88%.
@article{arxiv.1710.08623,
title = {Hand Gesture Recognition Using Ultrasonic Waves},
author = {Mohammed H. AlSharif and Mohamed Saad and Tareq Y. Al-Naffouri},
journal= {arXiv preprint arXiv:1710.08623},
year = {2017}
}