TY - JOUR
ID - bulling09_jaise
T1 - Wearable EOG goggles: Seamless sensing and context-awareness in everyday environments
A1 - Bulling, Andreas
A1 - Roggen, Daniel
A1 - Tröster, Gerhard
JA - Journal of Ambient Intelligence and Smart Environments
Y1 - 2009
VL - 1
IS - 2
SP - 157
EP - 171
SN - 1876-1364
M2 - doi: 10.3233/AIS-2009-0020
KW - Activity Recognition
KW - Context-awareness
KW - Electrooculography (EOG)
KW - Human-Computer Interaction (HCI)
KW - Wearable Eye Tracking
N2 - In this article we introduce the analysis of eye motion as a new input modality for activity recognition, context-awareness and mobile HCI applications. We describe a novel embedded eye tracker that, in contrast to common systems using video cameras, relies on Electrooculography (EOG). This self-contained wearable device consists of goggles with dry electrodes integrated into the frame and a small pocket-worn component with a DSP for real-time EOG signal processing. It can store data locally for long-term recordings or stream processed EOG signals to a remote device over Bluetooth. We show how challenges associated with wearability, eye motion analysis and signal artefacts caused by physical activity can be addressed with a combination of a special mechanical design, optimised algorithms for eye movement detection and adaptive signal processing. In two case studies, we demonstrate that EOG is a suitable measurement technique for the recognition of reading activity and eye-based human-computer interaction. Eventually, wearable EOG goggles may pave the way for seamless eye movement analysis and new forms of context-awareness not possible today.
ER -