Sensor fusion using EMG and vision for hand gesture classification in mobile applications

TL;DR

This paper presents a sensor fusion framework combining EMG and vision data, including a new dataset, to enhance hand gesture recognition accuracy on mobile devices, achieving significant improvements over individual sensors.

Contribution

It introduces a novel multisensor fusion framework with a new publicly available dataset for hand gesture recognition on mobile platforms.

Findings

Fusion improves accuracy by 13% over EMG alone

Fusion improves accuracy by 11% over vision alone

Achieved 85% recognition accuracy on mobile devices

Abstract

The discrimination of human gestures using wearable solutions is extremely important as a supporting technique for assisted living, healthcare of the elderly and neurorehabilitation. This paper presents a mobile electromyography (EMG) analysis framework to be an auxiliary component in physiotherapy sessions or as a feedback for neuroprosthesis calibration. We implemented a framework that allows the integration of multisensors, EMG and visual information, to perform sensor fusion and to improve the accuracy of hand gesture recognition tasks. In particular, we used an event-based camera adapted to run on the limited computational resources of mobile phones. We introduced a new publicly available dataset of sensor fusion for hand gesture recognition recorded from 10 subjects and used it to train the recognition models offline. We compare the online results of the hand gesture recognition using the fusion approach with the individual sensors with an improvement in the accuracy of 13% and 11%, for EMG and vision respectively, reaching 85%.