Gaze Estimation Method Using Analysis of Electrooculogram Signals and Kinect Sensor

Abstract

A gaze estimation system is one of the communication methods for severely disabled people who cannot perform gestures and speech. We previously developed an eye tracking method using a compact and light electrooculogram (EOG) signal, but its accuracy is not very high. In the present study, we conducted experiments to investigate the EOG component strongly correlated with the change of eye movements. The experiments in this study are of two types: Experiments to see objects only by eye movements and experiments to see objects by face and eye movements. The experimental results show the possibility of an eye tracking method using EOG signals and a Kinect sensor.