Back to results
US 10,895,910 B2Granted
Adaptive eye-tracking calibration method
AssigneeNational Taiwan University
InventorsShao-Yi Chien, Liang Fang
Life of this patent
Estimating the term…
Abstract
An adaptive eye-tracking calibration method includes generating an eye model acting as a current eye model; calibrating the eye model; comparing real-time pupil data set and pupil data set of the current eye model to obtain a pupil data difference when an event happens; and generating a new eye model if the pupil data difference is greater than a predetermined threshold.
Claims14
An adaptive eye-tracking calibration method, comprising:
- (a) generating an eye model acting as a current eye model;
- (b) calibrating the eye model;
- (c) detecting whether at least an event happens, wherein the event includes that a predetermined time interval elapses;
- (d) comparing real-time pupil data set and pupil data set of the current eye model to obtain a pupil data difference when the event happens, otherwise repeating step (c);
- and
- (e) generating a new eye model if the pupil data difference is greater than a predetermined threshold, otherwise updating the current eye model according to the real-time pupil data set if the pupil data difference is not greater than the predetermined threshold.
3 more elements
An adaptive eye-tracking calibration method, comprising:
- (a) collecting a plurality of pupil images to obtain corresponding pupil data set, according to which an eye model is generated to act as a current eye model;
- (b) obtaining an optical axis according to the eye model;
- (c) obtaining a visual axis based on at least one calibration point;
- (d) calibrating the eye model according to a difference between the visual axis and the optical axis;
- (e) determining whether at least an event happens, wherein the event includes that a predetermined time interval elapses;
- (f) comparing real-time pupil data set and pupil data set of the current eye model to obtain a pupil data difference when the event happens, otherwise repeating step (e);
- and
- (g) generating a new eye model if the pupil data difference is greater than a predetermined threshold, otherwise updating the current eye model according to the real-time pupil data set if the pupil data difference is not greater than the predetermined threshold.
5 more elements
Dependencies are inferred from the claim text.