Method and device for carrying out eye gaze mapping
The invention relates to a device and a method for performing an eye gaze mapping (M), in which at least one point of vision (B) and/or a viewing direction of at least one person ( 10 ) in relation to at least one scene recording (S) of a scene ( 12 ) viewed by the at least one person ( 10 ) is mapped onto a reference (R). At least a part of an algorithm (A 1 , A 2 , A 3 ) for performing the eye gaze mapping (M) is thereby selected from multiple predetermined algorithms (A 1 , A 2 , A 3 ) as a function of at least one parameter (P), and the eye gaze mapping (M) is performed on the basis of the at least one part of the algorithm (A 1 , A 2 , A 3 ).
1. A method comprising:
at a plurality of times, concurrently obtaining a scene image of a scene and a corresponding eye tracking measurement of a user;
determining an image quality characterizing the plurality of scene images;
determining, based on the plurality of scene images, a dynamism parameter of the scene;
in response to the image quality being less than a threshold quality, utilizing a first type of mapping to map a plurality of points of view of the user to a reference representation of the scene based on the plurality of scene images, the plurality of corresponding eye tracking measurements and the dynamism parameter; and
in response to the image quality being greater than the threshold quality, utilizing a second type of mapping to map the plurality of points of view of the user to the reference representation of the scene based on the plurality of scene images, the plurality of corresponding eye tracking measurements and the dynamism parameter.
2. The method of claim 1 , further comprising:
in accordance with a determination that the dynamism parameter indicates a first value, mapping the plurality of points of view according to a first algorithm; and
in accordance with a determination that the dynamism parameter indicates a second value, mapping the plurality of points of view according to a second algorithm different than the first algorithm.
3. The method of claim 1 , wherein determining the dynamism parameter of the scene includes classifying the scene into one of a plurality of predefined groups.
4. The method of claim 1 , wherein the dynamism parameter indicates an amount of temporal variability of the scene.
5. The method of claim 1 , wherein the dynamic parameter indicates whether the scene is a static scene or a moving scene.
6. The method of claim 5 , further comprising:
in accordance with a determination that the dynamism parameter indicates that the scene is a moving scene, mapping the plurality of points of view according to a first algorithm; and
in accordance with a determination that the dynamism parameter indicates that the scene is a static scene, mapping the plurality of points of view according to a second algorithm that is more computationally efficient that the first algorithm.
7. The method of claim 1 , wherein the dynamism parameter indicates whether a background of the scene is temporally unchanging or temporally variable.
8. The method of claim 7 , further comprising:
in accordance with a determination that the dynamism parameter indicates that the background of the scene is temporally unchanging, mapping the plurality of points of view according to a first algorithm that ignores the background; and
in accordance with a determination that the dynamism parameter indicates that the background of the scene is temporally variable, mapping the plurality of points of view according to a second algorithm in which the background is analyzed.
9. The method of claim 1 , wherein the dynamism parameter indicates objects of the scene that are moving or varying.
10. The method of claim 1 , wherein mapping the plurality of points of view includes:
determining, based on the plurality of scene images of the scene and the plurality of corresponding eye tracking measurements, a corresponding plurality of viewpoints of a reference image of the scene.
11. The method of claim 10 , wherein at least one of the plurality of scene images of the scene is from a different perspective than the reference image of the scene.
12. The method of claim 1 , wherein the second type of mapping operates in a shorter time duration than the first type of mapping.
13. The method of claim 1 , wherein the first type of mapping utilizes image analysis of a greater complexity than the second type of mapping.
14. An apparatus comprising:
a scene camera to capture a plurality of scene images of a scene;
an eye tracker to generate a plurality of corresponding eye tracking measurements concurrently obtained with the plurality of scene images of the scene; and
a processor to:
determine an image quality characterizing the plurality of scene images;
determine, based on the plurality of scene images, a dynamism parameter of the scene;
in response to the image quality being less than a threshold quality, utilize a first type of mapping to map a plurality of points of view of the user to a reference representation of the scene based on the plurality of scene images, the plurality of corresponding eye tracking measurements and the dynamism parameter; and
in response to the image quality being greater than the threshold quality, utilizing a second type of mapping to map the plurality of points of view of the user to the reference representation of the scene based on the plurality of scene images, the plurality of corresponding eye tracking measurements and the dynamism parameter.
15. The apparatus of claim 14 , wherein the processor is to:
in accordance with a determination that the dynamism parameter indicates a first value, map the plurality of points of view according to a first algorithm; and
in accordance with a determination that the dynamism parameter indicates a second value, map the plurality of points of view according to a second algorithm different than the first algorithm.
16. The apparatus of claim 14 , wherein the dynamism parameter indicates an amount of temporal variability of the scene.
17. The apparatus of claim 14 , wherein the dynamic parameter indicates whether the scene is a static scene or a moving scene.
18. The apparatus of claim 14 , wherein the dynamism parameter indicates whether a background of the scene is temporally unchanging or temporally variable.
19. A non-transitory computer-readable medium encoding instructions which, when executed, cause a processor to perform operations comprising:
at a plurality of times, concurrently obtaining a scene image of a scene and a corresponding eye tracking measurement of a user;
determining an image quality characterizing the plurality of scene images;
determining, based on the plurality of scene images, a dynamism parameter of the scene;
in response to the image quality being less than a threshold quality, utilizing a first type of mapping to map a plurality of points of view of the user to a reference representation of the scene based on the plurality of scene images, the plurality of corresponding eye tracking measurements and the dynamism parameter; and
in response to the image quality being greater than the threshold quality, utilizing a second type of mapping to map the plurality of points of view of the user to the reference representation of the scene based on the plurality of scene images, the plurality of corresponding eye tracking measurements and the dynamism parameter.
20. The non-transitory computer-readable medium of claim 19 , wherein the operations further comprise:
in accordance with a determination that the dynamism parameter indicates a first value, mapping the plurality of points of view according to a first algorithm; and
in accordance with a determination that the dynamism parameter indicates a second value, mapping the plurality of points of view according to a second algorithm different than the first algorithm.
21. The non-transitory computer-readable medium of claim 19 , wherein the dynamism parameter indicates an amount of temporal variability of the scene.
22. The non-transitory computer-readable medium of claim 19 , wherein the dynamism parameter indicates whether a background of the scene is temporally unchanging or temporally variable.