Research on Gaze Estimation Method Combined with Head Motion Changes

Abstract

The line of sight reflects the focus of human attention. Gaze estimation technology has a wide range of application prospects in human-computer interaction, human emotion analysis, commercial advertising, and so on. Gaze estimation needs to be jointly determined by eye movement and head movement because the human gaze is often with the head movement. In this paper, a gaze estimation system with head movement is implemented by a monocular camera, using eye movement features and head movement posture changes to estimate the gaze point. A camera is used as the information acquisition device to extract the eye movement feature information, and the offset of head movement is estimated at the same time. The final fixation point position coordinates are obtained by compensating the fixation point position in the case of head movement, and then the fixation point position coordinates are estimated. For the compensated gaze drop point, the average pixel error on the X-axis is estimated to be 118 pixels, and the average pixel error on the Y-axis is estimated to be 136 pixels.