Adaptive Regulation of CCD Camera in Eye Gaze Tracking System

To capture eye images with good quality in the eye gaze tracking system, a strategy to track and aim at the eye is proposed, and an automatic method, which combines the regulation of the aperture with the adjustment of the focus of the camera lens, is developed. Firstly, the geometrical positions of LEDs, camera, cornea and glints are analyzed. The image´s average brightness value is utilized to control the aperture of the lens, and then the glints information can be obtained to control a pan-tilt unit for aiming at and tracking the eye, and to adjust the focus lens. If the pupil contour can be extracted from the image, the average gradient value of the pupil edge points can be used for real-time focusing. Experiments show that this system can adapt to external lighting changes and to the head movements, and it can track the eye and acquire clear eye images in real-time.