WaveGlove: Transformer-based hand gesture recognition using multiple inertial sensors

TL;DR

WaveGlove introduces a multi-sensor glove and a Transformer-based model that significantly improves hand gesture recognition accuracy, especially for complex gestures, by leveraging multiple inertial sensors and extensive datasets.

Contribution

The paper presents a novel multi-sensor glove hardware and a Transformer-based approach, demonstrating enhanced gesture recognition performance over single-sensor methods.

Findings

Multiple sensors improve recognition accuracy for complex gestures.

Using up to three sensors yields optimal performance gains.

Transformer architecture outperforms traditional models in this task.

Abstract

Hand Gesture Recognition (HGR) based on inertial data has grown considerably in recent years, with the state-of-the-art approaches utilizing a single handheld sensor and a vocabulary comprised of simple gestures. In this work we explore the benefits of using multiple inertial sensors. Using WaveGlove, a custom hardware prototype in the form of a glove with five inertial sensors, we acquire two datasets consisting of over $11000$ samples. To make them comparable with prior work, they are normalized along with $9$ other publicly available datasets, and subsequently used to evaluate a range of Machine Learning approaches for gesture recognition, including a newly proposed Transformer-based architecture. Our results show that even complex gestures involving different fingers can be recognized with high accuracy. An ablation study performed on the acquired datasets demonstrates the importance of multiple sensors, with an increase in performance when using up to three sensors and no significant improvements beyond that.