Eye tracking with two-dimensional collision detection area and determined interactive component

1 . An eye tracking method, comprising:

obtaining a sight start point, a sight direction, a fixation point of a sight on a two-dimensional (2D) interactive panel in an extended reality space of a user, and a size parameter of a collision detection area on the interactive panel, wherein the collision detection area is a 2D graphic;

determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area;

determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel; and

when there are a plurality of candidate components in the interactive panel, determining one interactive component from the plurality of candidate components based on position relationships between the plurality of candidate components and the sight start point, and the sight direction, wherein

the size parameter of the collision detection area is a radius of a sphere, and

the determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area comprises:

determining the collision detection area based on the radius of the sphere and using the position of the fixation point as a center point.

2 . The method according to claim 1 , wherein the determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel comprises:

determining a plurality of sampling points in the collision detection area according to a preset sampling manner; and

determining an interactive component that contains the sampling point as the candidate component based on positions of the sampling points and the positions of the interactive components.

3 . The method according to claim 1 , wherein the collision detection area is a circular or elliptical area.

4 . The method according to claim 1 , wherein

the collision detection area is a square or rectangular area, and

the determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel comprises:

determining whether the interactive component collides with the square or rectangular collision detection area based on the position of the square or rectangular collision detection area and the positions of the interactive component;

when the interactive component collides with the square or rectangular collision detection area, determining that the interactive component is the candidate component.

5 . The method according to claim 4 , wherein

the determining the collision detection area based on the radius of the sphere and using the position of the fixation point as a center point comprises:

determining a length of a major axis of an ellipse or a diameter of a circle formed by projecting the sphere onto the interactive panel based on the radius of the sphere and an included angle between the sight direction and the interactive panel; and

determining the square or rectangular collision detection area based on the length of the major axis of the ellipse or the diameter of the circle and using the position of the fixation point as a center point.

6 . The method according to claim 1 , wherein, before the when there are a plurality of candidate components in the interactive panel, determining one interactive component from the plurality of candidate components based on position relationships between the plurality of candidate components and the sight start point, and the sight direction, the method further comprises:

filtering the plurality of candidate components based on a hierarchical relationship between components in the interactive panel.

7 . The method according to claim 6 , wherein the filtering the plurality of candidate components based on a hierarchical relationship between components in the interactive panel comprises:

when it is determined that the hierarchical relationship between the plurality of candidate components is a nesting relationship based on the hierarchical relationship between the components in the interactive panel, filtering out the candidate component located at a bottom layer.

8 . The method according to claim 1 , wherein the determining one interactive component from the plurality of candidate components based on position relationships between the plurality of candidate components and the sight start point, and the sight direction comprises:

determining collision points of the plurality of candidate components, wherein the collision points are points on the candidate components that are closest to the sight direction;

determining an interactive score of each candidate component based on a position relationship between the collision point of the candidate component and the sight start point, the sight direction, and center point of the candidate component; and

determining the interactive component from the plurality of candidate components based on the interactive score of each candidate component.

9 . The method according to claim 8 , wherein the determining collision points of the plurality of candidate components comprises:

traversing the plurality of candidate components, and when the fixation point is located in a current candidate component, determining the fixation point as a collision point of the current candidate component;

when the fixation point is located outside the current candidate component, determining a first point in the current candidate component that is closest to the sight direction; and

determining the first point as the collision point of the current candidate component.

10 . The method according to claim 9 , wherein the determining the first point as the collision point of the current candidate component comprises:

if a distance between the sight direction and the first point is less than or equal to a first distance threshold, determining the first point as the collision point of the current candidate component, wherein the first distance threshold is determined based on the size of the collision detection area; and

if the distance between the sight direction and the first point is greater than the first distance threshold, filtering out the current candidate component.

11 . The method according to claim 9 , wherein the determining a first point in the current candidate component that is closest to the sight direction comprises:

if the current candidate component is blocked by a first candidate component, determining a boundary of an unblocked part of the current candidate component based on a position of the first candidate component; and

determining a first point in the unblocked part of the current candidate component that is closest to the sight direction.

12 . The method according to claim 8 , wherein the determining an interactive score of each candidate component based on a position relationship between the collision point of the candidate component and the sight start point, the sight direction, and a center point of the candidate component comprises:

calculating a first distance between the collision point of each candidate component and the sight start point based on the position of the sight start point and the position of the collision point of the candidate component;

determining a collision direction of each candidate component using the sight start point as a start point and the collision point of the candidate component as an end point, and determining a first included angle between the collision direction of each candidate component and the sight direction;

calculating a second distance between the collision point and the center point of each candidate component based on the position of the collision point and a position of the center point of the candidate component;

determining a center direction of each candidate component using the sight start point as a start point and the center point of the candidate component as an end point, and determining a second included angle between the center direction of the candidate component and the sight direction; and

performing a weighted operation on the first distance, the first included angle, the second distance, and the second included angle of each candidate component to obtain the interactive score of the candidate component.

13 . The method according to claim 1 , wherein, before the obtaining a sight start point, a sight direction, a fixation point of a sight on a two-dimensional (2D) interactive panel in an extended reality space of a user, and a size parameter of a collision detection area on the interactive panel, the method further comprises:

selecting the interactive panel based on an eye movement parameter.

14 . The method according to claim 1 , wherein, after the determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area, the method further comprises:

displaying the collision detection area based on the position of the collision detection area.

15 . The method according to claim 14 , wherein the collision detection area is suspended on the interactive panel, and the collision detection area is translucent.

16 . An extended reality device, comprising:

a processor and a memory, wherein the memory is configured to store a computer program, and the processor is configured to call and run the computer program stored in the memory to perform an eye tracking method, comprising:

obtaining a sight start point, a sight direction, a fixation point of a sight on a two-dimensional (2D) interactive panel in an extended reality space of a user, and a size parameter of a collision detection area on the interactive panel, wherein the collision detection area is a 2D graphic;

determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area;

determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel; and

when there are a plurality of candidate components in the interactive panel, determining one interactive component from the plurality of candidate components based on position relationships between the plurality of candidate components and the sight start point, and the sight direction, wherein

the size parameter of the collision detection area is a radius of a sphere, and

the determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area comprises:

determining the collision detection area based on the radius of the sphere and using the position of the fixation point as a center point.

17 . The extended reality device according to claim 16 , wherein

the determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel comprises:

determining a plurality of sampling points in the collision detection area according to a preset sampling manner; and

determining an interactive component that contains the sampling point as the candidate component based on positions of the sampling points and the positions of the interactive components.

18 . The extended reality device according to claim 17 , wherein the collision detection area is a circular or elliptical area.

19 . A non-transitory computer-readable storage medium, being configured to store a computer program, wherein the computer program enables a computer to perform an eye tracking method, comprising:

obtaining a sight start point, a sight direction, a fixation point of a sight on a two-dimensional (2D) interactive panel in an extended reality space of a user, and a size parameter of a collision detection area on the interactive panel, wherein the collision detection area is a 2D graphic;

determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area;

determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel; and

when there are a plurality of candidate components in the interactive panel, determining one interactive component from the plurality of candidate components based on position relationships between the plurality of candidate components and the sight start point, and the sight direction, wherein the size parameter of the collision detection area is a radius of a sphere, and

the determining a position of the collision detection area based on a position of the fixation point and the size parameter of the collision detection area comprises:

determining the collision detection area based on the radius of the sphere and using the position of the fixation point as a center point.

20 . The non-transitory computer-readable storage medium according to claim 19 , wherein the determining an interactive candidate component collided with the collision detection area based on the position of the collision detection area and positions of interactive components on the interactive panel comprises:

determining a plurality of sampling points in the collision detection area according to a preset sampling manner; and

determining an interactive component that contains the sampling point as the candidate component based on positions of the sampling points and the positions of the interactive components.