Pupil detection and gaze tracking using a deformable template

2020 
This paper suggests a method for tracking gaze of a person at a distance around 2 m, using a single pan-tilt-zoom (PTZ) camera. In the suggested method, images are acquired for gaze tracking by turning the camera to the wide angle mode, or the narrow angle mode, depending on the location of the person. The face that is present in the field of view (FOV) of a camera, is detected in the wide angle mode. Once the location of the face is calculated, the camera turns to the narrow angle mode. The images, which have been acquired in the narrow angle mode, contain information on the direction of gaze of the person, who is at a distance. The method for calculating the direction of gaze is comprised of the head pose estimation and gaze direction calculation steps. The head pose estimation is performed using the location information on the eyes and nose in the face. The direction of gaze is generated using the process of partitioning the pupil through a deformable template, and extracting the center of an eye using the end points of both eyes and head pose information. This paper shows that the proposed gaze tracking algorithm can effectively track the direction of a person’s gaze, at varying distances.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    31
    References
    1
    Citations
    NaN
    KQI
    []