Forearm Ultrasound based Gesture Recognition on Edge

TL;DR

This paper presents an end-to-end, real-time forearm ultrasound gesture recognition system optimized for edge devices, achieving high accuracy and low latency through quantization techniques.

Contribution

It introduces a deep neural network deployment on edge devices for ultrasound-based gesture recognition, emphasizing model size reduction and real-time performance.

Findings

Achieved 92% accuracy with Float16 quantization.

Inference time of 0.31 seconds on Raspberry Pi.

Demonstrated feasibility of wearable ultrasound gesture systems.

Abstract

Ultrasound imaging of the forearm has demonstrated significant potential for accurate hand gesture classification. Despite this progress, there has been limited focus on developing a stand-alone end- to-end gesture recognition system which makes it mobile, real-time and more user friendly. To bridge this gap, this paper explores the deployment of deep neural networks for forearm ultrasound-based hand gesture recognition on edge devices. Utilizing quantization techniques, we achieve substantial reductions in model size while maintaining high accuracy and low latency. Our best model, with Float16 quantization, achieves a test accuracy of 92% and an inference time of 0.31 seconds on a Raspberry Pi. These results demonstrate the feasibility of efficient, real-time gesture recognition on resource-limited edge devices, paving the way for wearable ultrasound-based systems.