Zero delay gaze filter
A method for processing a gaze signal in an eye tracking system is provided. The method comprises receiving a first image of a user's eye captured at a first point in time and a second image of the users eye captured at a second point in time subsequent to the first point in time, and determining, based on the first image and the second image, whether eye movement of the user's eye is in fixation or not. The method may further comprise to, on condition that the eye movement of the users eye is in fixation, applying a filter on the gaze signal, wherein the filter is adapted to decrease variance in the gaze signal.
1. A method for processing a gaze signal in an eye tracking system, the method comprising:
receiving a first image of a user's eye captured at a first point in time and a second image of the user's eye captured at a second point in time subsequent to the first point in time;
determining, based on the first image and the second image, whether eye movement of the user's eye is in fixation or not, wherein the determining comprises ascertaining that a pixel has changed on condition that a difference between a value of the pixel in the first image and a value of the corresponding pixel in the second image is above a first predetermined threshold, and
wherein the determining further comprises ascertaining that the eye movement of the user's eye is in fixation on condition that an accumulated number of changed pixels of the images is below a second predetermined threshold;
on condition that the eye movement of the user's eye is in fixation, applying a filter on the gaze signal, wherein the filter is adapted to decrease variance in the gaze signal.
2. The method according to claim 1 , further comprising, on condition that the eye movement of the user's eye is not in fixation, refrain from applying the filter on the gaze signal.
3. The method according to claim 1 , wherein the filter is a low-pass filter.
4. The method according to claim 1 , wherein the first image originates from a first original image cropped based on a position of the pupil of the eye in the first original image and the second image originates from a second original image cropped based on a position of the pupil of the eye in the second original image.
5. The method according to claim 1 , wherein the determining comprises determining a difference between a value of a pixel of the first image with a value of a corresponding pixel in the second image, and wherein the determining further comprises determining that the eye movement of the user's eye is in fixation on condition that an accumulated difference of pixel values of the images is below a predetermined threshold.
6. The method according to claim 1 , wherein, on condition that less than a predetermined number of pixels in the first image have corresponding pixels in the second image, determining that the eye movement of the user's eye is non-fixated.
7. The method according to claim 1 , wherein the determining comprises applying a machine learning logic.
8. The method according to claim 1 , wherein the determining is further based on a previous determination that the eye movement the user's eye is in fixation or not.
9. The method according to claim 1 , wherein the determining is further based on a third image captured at a third point in time, the third point in time being before the first point in time and the second point in time, and wherein the third point in time and the first point in time are within a time period in which the eye movement of the user's eye is determined to be continuously fixated.
10. The method according to claim 1 , wherein the first image and the second image originate from images captured by a camera arranged at a substantially fixated position relative to the user's eye when using the system.
11. A system for eye tracking, comprising:
a camera for capturing images of a user's eye;
a processing unit configured to perform the method of:
receiving a first image of a user's eye captured at a first point in time and a second image of the user's eye captured at a second point in time subsequent to the first point in time;
determining, based on the first image and the second image, whether eye movement of the user's eye is in fixation or not, wherein the determining comprises ascertaining that a pixel has changed on condition that a difference between a value of the pixel in the first image and a value of the corresponding pixel in the second image is above a first predetermined threshold, and
wherein the determining further comprises ascertaining that the eye movement of the user's eye is in fixation on condition that an accumulated number of changed pixels of the images is below a second predetermined threshold;
on condition that the eye movement of the user's eye is in fixation, applying a filter on the gaze signal, wherein the filter is adapted to decrease variance in the gaze signal.
12. The system according to claim 11 , wherein the camera is arranged at a substantially fixed position relative to the user's eye when using the system.
13. The system according to claim 11 , comprised in an augmented reality, AR, system or virtual reality, VR, system.
14. The system according to claim 13 , wherein the AR or VR system is wearable.