Methods and systems for player location determination in gameplay with a mobile device
Methods and systems for detecting a player in a gaming environment using a mobile device are disclosed. The methods and systems perform the steps of receiving calibration data from a camera of a user device, the calibration data comprising a first reference point associated with the gaming environment, a second reference point associated with the gaming environment, and sensor data associated with the user device; computing a camera projection based on the first reference point, the second reference point, and the sensor data obtained from the user device; receiving an input video of the gaming environment, wherein the input video is captured using the camera, and wherein frames of the input video comprise at least one player in the gaming environment; identifying an image location of the player by performing a computer vision algorithm on the input video; and determining a real-world location of the player based on the image location and the camera projection.
1. A method for detecting location of at least one player in a gaming environment, comprising:
receiving calibration data from a camera of a user device, the calibration data comprising a first reference point associated with the gaming environment, a second reference point associated with the gaming environment, and sensor data associated with the user device, wherein the first reference point corresponds to a player's location at a first feature location in the gaming environment during calibration;
computing a camera projection based on the first reference point, the second reference point, and the sensor data obtained from the user device;
receiving an input video of the gaming environment, wherein the input video is captured using the camera, and wherein frames of the input video comprise at least one player in the gaming environment;
identifying an image location of the at least one player by performing a computer vision algorithm on the input video; and
determining a real-world location of the at least one player based on the image location and the camera projection.
2. The method of claim 1 , wherein the user device is positioned on a ground level or substantially proximate to the ground level.
3. The method of claim 1 , wherein the calibration data is generated by calibrating the camera by providing instructions to position the player at the first feature location in the gaming environment corresponding to the first reference point.
4. The method of claim 1 , wherein the first reference point is determined based at least in part on a determination of a body part of the player located at the first feature location.
5. The method of claim 4 , wherein the determination of the body part of the player further comprises a determination of a dimension of the body part of the player.
6. The method of claim 5 , wherein the dimension of the body part of the player is utilized in the determining of the real-world location of the player.
7. The method of claim 5 , wherein the dimension of the body part of the player is utilized in verifying a consistency of the calibration data.
8. The method of claim 4 , wherein the second reference point comprises a second feature location of the gaming environment different from the first feature location of the gaming environment.
9. The method of claim 1 , wherein the camera projection is a camera projection matrix computed from a first reference point correspondence between the first reference point at a first real-world location and at a first image location, and a second reference point correspondence between the second reference point at a second real-world location and at a second image location.
10. The method of claim 9 , wherein the sensor data comprises a camera intrinsic matrix of the camera.
11. The method of claim 10 , wherein the sensor data further comprises an accelerometer data from the user device.
12. The method of claim 1 , wherein the gaming environment is basketball, and wherein the first reference point is the player's location at a known ground location.
13. The method of claim 12 , wherein the second reference point is a hoop at a known hoop location.
14. The method of claim 1 , further comprising:
estimating a camera height comprising a distance between the user device and a ground level, the camera height estimated from the input video.
15. The method of claim 14 , wherein a foot location of the player at the first feature location is utilized for the first reference point when the camera height exceeds a given threshold.
16. The method of claim 14 , wherein a head location of the player at the first feature location is utilized for the first reference point when the camera height is below a given threshold.
17. The method of claim 14 , wherein the camera height is utilized in the computing of the camera projection.
18. A non-transitory storage medium storing executable instructions, the executable instructions when executed by a hardware processor causes the hardware processor to execute a process for detecting location of at least one player in a gaming environment, the executable instructions comprising program code to:
receive calibration data from a camera of a user device, the calibration data comprising a first reference point associated with the gaming environment, a second reference point associated with the gaming environment, and sensor data associated with the user device, wherein the first reference point corresponds to a player's location at a first feature location in the gaming environment during calibration;
compute a camera projection based on the first reference point, the second reference point, and the sensor data obtained from the user device;
receive an input video of the gaming environment, wherein the input video is captured using the camera, and wherein frames of the input video comprise at least one player in the gaming environment;
identify an image location of the at east one player by performing a computer vision algorithm on the input video; and
determine a real-world location of the at least one player based on the image location and the camera projection.
19. The non-transitory storage medium of claim 18 , wherein the calibration data is generated by calibrating the camera by providing instructions to position the player at the first feature location in the gaming environment corresponding to the first reference point.
20. A system comprising a non-transitory storage medium storing executable instructions and a processor, the executable instructions when executed by the processor causes the processor to execute a process for detecting location of at least one player in a gaming environment, the executable instructions comprising program code to:
receive calibration data from a camera of a user device, the calibration data comprising a first reference point associated with the gaming environment, a second reference point associated with the gaming environment, and sensor data associated with the user device, wherein the first reference point corresponds to a player's location at a first feature location in the gaming environment during calibration;
compute a camera projection based on the first reference point, the second reference point, and the sensor data obtained from the user device;
receive an input video of the gaming environment, wherein the input video is captured using the camera, and wherein frames of the input video comprise at least one player in the gaming environment;
identify an image location of the at least one player by performing a computer vision algorithm on the input video; and
determine a real-world location of the at least one player based on the image location and the camera projection.