Exploring EMG gesture recognition - interactive armband for audio playback control

Abstract

This paper investigates the potential of using an electromyographic gesture recognition armband as an everyday companion for operating mobile devices in awareness-requiring contexts and suggests the fields, in which further developments are advisable. The Myo armband from Thalmic Labs is a fully functional motion controller, based on gesture recognition through EMG muscle sensing. The device has been applied for audio control, and the usability and relevance of the gestural interaction have been examined. Participants were asked to operate on a recording while cycling, and a reference group performed similar task in leisure context. The gathered answers suggest decent potential of gestural interaction manner for environments requiring high visual attention, eg. driving or cycling. However, the current state of the solution acts in too sensitive way, as processing numerous misinterpreted gestures highly decreases the system's usability. Moreover, gestures employed are perceived as too apparent and intrusive for social interactions.

Hand Gestures Recognition for Human-Machine Interfaces: A Low-Power Bio-Inspired Armband

“…Therefore, the large availability of commercial devices and the knowledge acquired by multiple research groups around the world made hand gesture recognition be involved in many HMI use-cases. Among the most active, we can find computer interaction [14], outdoor music handling [15], biomedical applications like prostheses [16]- [18] and robotic arm control [6], [19], [20], or even sign language communication [21], [22], which requires a lot of sensitivity in recognizing each single finger movements. Furthermore, by exploiting the other actor of the HMI (i.e., the machine), hand gesture recognition can be involved also in the (tele-)rehabilitation field, both with passive and active approaches.…”