A study on gaze estimation system using the direction of eyes and face

The aim of this study is to present electrooculogram signals and Kinect sensor (RGB-D sensor) that can be used as a human interface efficiently. The gaze estimation using eyes and face is also important in study for preventing traffic accidents. In this paper, we introduce eye movement tracking system using cross-channels electrooculogram signals and RGB-D sensor for face tracking. Thus, gaze estimation system can be established by both eye movement and face tracking. In order to confirm the effectiveness of our proposal system, we tried the experiments in an environment in which the experimental subjects can move freely eyes and head. As the results of the experiments, angle of 30°, 60°,-30°,-60° gaze estimation is recognized with high accuracy in our system. In addition, the identification rate of each angle is also high accuracy.