Method for operating an eye tracking device for multi-user eye tracking and eye tracking device
The invention relates to a method for operating an eye tracking device ( 10 ) for multi-user eye tracking, wherein images ( 24 ) of a predefined capturing area ( 14 ) of the eye tracking device ( 10 ) are captured by means of an imaging device ( 12 ) of the eye tracking device ( 10 ) and the captured images ( 24 ) are processed by means of a processing unit ( 16 ) of the eye tracking device ( 10 ). If a first user ( 26 a ) and a second user ( 26 b ) are present in the predefined capturing area ( 14 ) of the eye tracking device ( 10 ), a first information relating to the first user ( 26 a ) and a second information relating to the second user ( 26 b ) are determined on the basis of the captured images ( 24 ) by processing the images ( 24 ). Furthermore the images ( 24 ) are captured successively in a predeterminable time sequence.
1. A method comprising:
capturing a first set of one or more images;
determining a value of a user search parameter based on one or more numbers of detected users in the first set of one or more images;
capturing a second set of a plurality of images;
selecting a subset of the second set of the plurality of images with a frequency based on the value of the user search parameter;
searching, in each of the subset of the second set of the plurality of images, for a representation of an undetected user; and
performing, for each of the second set of the plurality of captured images, eye tracking upon a representation of a detected user, wherein performing eye tracking upon the representation of the detected user is performed using a portion of the image and searching for a representation of an undetected user is performed on the entire image.
2. The method of claim 1 , wherein the user search parameter is based on a number of currently detected users in the first set of one or more images.
3. The method of claim 2 , wherein the subset includes fewer of the second set of the plurality of images when the number of currently detected users is greater.
4. The method of claim 1 , wherein the user search parameter is based on an average number of detected users in the first set of one or more images.
5. The method of claim 4 , wherein the subset includes fewer of the second set of the plurality of images when the average number of detected users in the first set of one or more images is less.
6. The method of claim 1 , wherein the user search parameter is based on a variation in the number of detected users in the first set of one or more images.
7. The method of claim 6 , wherein the subset includes fewer of the second set of the plurality of images when the variation in the number of detected users in the first set of the one of more images is less.
8. The method of claim 1 , wherein the subset of second set of the plurality of images includes less than all of the second set of the plurality of images.
9. The method of claim 1 , further comprising:
capturing a third set of a plurality of images;
determining a second value of the user search parameter;
selecting a subset of the third set of the plurality of images with a second frequency based on the second value of the user search parameter, wherein the second frequency is different than the frequency; and
searching, in each of the subset of the third set of the plurality of images, for a representation of an undetected user.
10. The method of claim 1 , wherein the numbers of detected users in the first set of one or more images includes at least one of zero detected users, one detected user, or two detected users.
11. An apparatus comprising:
a camera configured to capture a first set of one or more images and a second set of a plurality of images;
a processor configured to:
determine a value of a user search parameter based on one or more numbers of detected users in the first set of one or more images;
select a subset of the second set of the plurality of images with a frequency based on the value of the user search parameter;
search, in each of the subset of the second set of the plurality of images, for a representation of an undetected user; and
perform, for each of the second set of the plurality of captured images, eye tracking upon a representation of a detected user,
wherein perform eye tracking upon the representation of the detected user is performed using a portion of the image and search for a representation of an undetected user is performed on the entire image.
12. The apparatus of claim 11 , wherein the user search parameter is based on a number of currently detected users in the first set of one or more images.
13. The apparatus of claim 11 , wherein the camera is further configured to capture a third set of a plurality of images and wherein the processor is further configured to:
determine a second value of the user search parameter;
select a subset of the third set of the plurality of images with a second frequency based on the second value of the user search parameter, wherein the second frequency is different than the frequency; and
search, in each of the subset of the third set of the plurality of images, for a representation of an undetected user.
14. A non-transitory computer-readable medium encoding instructions which, when executed, cause a processor to perform operations comprising:
determining a value of a user search parameter based on one or more numbers of detected user in a first set of one or more captured images;
select, from a second set of a plurality of captured images, a subset of the second set of the plurality of captured images with a frequency based on the value of the user search parameter;
search, in each of the subset of the second set of the plurality of captured images, for a representation of an undetected user; and
perform, for each of the second set of the plurality of captured images, eye tracking upon a representation of a detected user, wherein perform eye tracking upon the representation of the detected user is performed using a portion of the image and search for a representation of an undetected user is performed on the entire image.