Selecting AR buttons on a hand
Systems and methods are provided for performing AR button selection operations on an augmented reality (AR) device. The system displays, by an AR device, a plurality of AR objects on a display region that overlaps a first real-world object, each of the plurality of AR objects being associated with an object selection region. The system computes a first spatial relationship factor for a first AR object of the plurality of AR objects based on a position of the first AR object relative to a position of a second real-world object and adjusts the object selection region of the first AR object based on the first spatial relationship factor. The system activates the first AR object in response to determining that the second real-world object overlaps the object selection region of the first AR object.
1. A method comprising:
displaying, by an AR device, a plurality of AR objects on a display region that overlaps a first real-world object, each of the plurality of AR objects being associated with an object selection region, a first AR object of the plurality of AR objects being associated with a first object selection region and a second AR object of the plurality of AR objects being associated with a second object selection region;
computing a first spatial relationship factor for the first AR object based on a position of the first AR object relative to a position of a second real-world object;
adjusting the first object selection region of the first AR object based on the first spatial relationship factor, the adjusting comprising rotating the first object selection region by a first number of degrees relative to the second object selection region in response to determining that the second real-world object is physically closer to the first AR object than the second AR object; and
activating the first AR object in response to determining that the second real-world object overlaps the object selection region of the first AR object.
2. The method of claim 1 , AR device comprises an AR eyewear device.
3. The method of claim 1 , further comprising:
detecting, by the AR device, the first and second real-world objects within a real-world environment by applying one or more machine learning models to an image of the real-world environment captured by a camera of the AR device.
4. The method of claim 1 , further comprising:
computing a second spatial relationship factor for the second AR object based on a position of the second AR object relative to the second real-world object; and
adjusting the second object selection region of the second AR object based on the second spatial relationship factor.
5. The method of claim 1 , wherein the first object selection region comprises a first three-dimensional (3D) height, size, and orientation, and wherein the second object selection region comprises a second 3D height, size, and orientation.
6. The method of claim 5 , further comprising configuring the first 3D height and size to be larger than the second 3D height and size in response to determining that the second real-world object is physically closer to selecting the first AR object than the second AR object.
7. The method of claim 1 , further comprising:
drawing a first line from a first center of the first AR object to a point on the second real-world object;
computing a vector representing directional velocity of the point on the second real-world object; and
generating the first spatial relationship factor as a function of the first line and the vector.
8. The method of claim 7 , further comprising:
determining a first alignment factor between the first line and the vector based on the first spatial relationship factor;
determining a second alignment factor between a second line drawn from a second center of a second AR object to the point on the second real-world object; and
comparing the first alignment factor with the second alignment factor.
9. The method of claim 8 , further comprising:
determining, based on the comparing, that the first alignment factor is better aligned than the second alignment factor.
10. The method of claim 9 , further comprising:
associating a larger dimension with the first object selection region of the first AR object than the second object selection region of the second AR object in response to determining that the first alignment factor is better aligned than the second alignment factor.
11. The method of claim 8 , wherein the first real-world object comprises a first real-world hand.
12. The method of claim 11 , wherein the second real-world object comprises a real-world stylus or a portion or finger of a second real-world hand.
13. The method of claim 7 , wherein the function comprises a dot product of the first line and the vector.
14. The method of claim 1 , wherein the plurality of AR objects comprises a virtual keypad or keyboard.
15. The method of claim 1 , further comprising:
scaling a size of each of the plurality of AR objects based on a size of the first real-world object.
16. The method of claim 1 , further comprising:
continuously adjusting the first object selection region as the first real-world object moves about a real-world environment.
17. The method of claim 1 , further comprising:
performing one or more operations in response to activating the first AR object.
18. A system comprising:
a storage device of an augmented reality (AR) device; and
at least one processor coupled to the storage device and configured to perform operations comprising:
displaying, by an AR device, a plurality of AR objects on a display region that overlaps a first real-world object, each of the plurality of AR objects being associated with an object selection region, a first AR object of the plurality of AR objects being associated with a first object selection region and a second AR object of the plurality of AR objects being associated with a second object selection region;
computing a first spatial relationship factor for the first AR object based on a position of the first AR object relative to a position of a second real-world object;
adjusting the first object selection region of the first AR object based on the first spatial relationship factor, the adjusting comprising rotating the first object selection region by a first number of degrees relative to the second object selection region in response to determining that the second real-world object is physically closer to the first AR object than the second AR object; and
activating the first AR object in response to determining that the second real-world object overlaps the object selection region of the first AR object.
19. The system of claim 18 , wherein the AR device comprises an AR eyewear device.
20. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
displaying, by an AR device, a plurality of AR objects on a display region that overlaps a first real-world object, each of the plurality of AR objects being associated with an object selection region, a first AR object of the plurality of AR objects being associated with a first object selection region and a second AR object of the plurality of AR objects being associated with a second object selection region;
computing a first spatial relationship factor for the first AR object based on a position of the first AR object relative to a position of a second real-world object;
adjusting the first object selection region of the first AR object based on the first spatial relationship factor, the adjusting comprising rotating the first object selection region by a first number of degrees relative to the second object selection region in response to determining that the second real-world object is physically closer to the first AR object than the second AR object; and
activating the first AR object in response to determining that the second real-world object overlaps the object selection region of the first AR object.