Computer Laboratory



These datasets contain video frames as individual images, and a text file describing the pupil ellipse in selected frames. The format of each line of the ellipse file is

<frame #> | <x>,<y>,<a>,<b>,<ϴ>

which describes the frame number and pupil ellipse, parametrised by its centre, major radius, minor radius and angle of the major axis with the x-axis (in radians).

If your use our datasets, please cite our paper.

Back to the project page.