This paper introduces our work towards implementing eye tracking on commodity devices. We describe our feature-based approach and the eye tracking system working on a commodity tablet. We recorded the data of 5 subjects following an animation on screen as reference. On the assumption that the position of device and user's head is stable, the average distance error between estimated gaze point to actual gaze point is around 12.23 [mm] using user-dependent training.
|出版物ステータス||Published - 2013|
|イベント||2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013 - Naha, Okinawa, Japan|
継続期間: 2013 11 5 → 2013 11 8
|Other||2013 2nd IAPR Asian Conference on Pattern Recognition, ACPR 2013|
|期間||13/11/5 → 13/11/8|
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition