Gaze tracking using one fixed camera

In this paper, a noncontact corneal-pupil reflection scheme using only one fixed camera to track the eye gaze is presented. A small manual focus lens is used in a camera without a pan-and-tilt base. A connected component labeling algorithm is designed to detect the pupils. The gradient information is utilized to find the precise pupil center. The effect of pupil detection precision to screen point estimation precision is also discussed. After the calibration process, the head movement is tracked by a Kalman filter. We experimented with the head roll compensation by using geometric information. The whole system can run in real time at video rate (25 frames/second). This pilot study shows that using a fixed camera has its own advantage in dynamic property and can achieve the same precision as more complex systems do.