Granted Patent B1

US 12,288,344 · App. 18/217,264 · Granted Apr 29, 2025

Inventors: Alan W. Marty (Menlo Park, CA); John Carter (Elkmont, AL)

Assignee: Pillar Vision, Inc.

G06T7/246G06T7/80H04N23/51G06T2207/10016G06T2207/30224G06T2207/30241

Abstract

Claims (41)

1. A method for calibrating a computing device to track basketball shots, comprising:

capturing a plurality of two-dimensional (2-D) images of a shot of a basketball toward a basketball hoop with a camera;

identifying the basketball in the plurality of 2-D images of the shot of the basketball;

identifying the basketball hoop in the plurality of 2-D images of the shot of the basketball;

determining distances of the basketball from the camera based on sizes of the basketball in the plurality of 2-D images of the shot of the basketball;

determining angles of the basketball from the camera for the plurality of 2-D images of the shot of the basketball based on positions of the basketball in of the plurality of 2-D images of the shot of the basketball;

calculating a parabolic trajectory of the basketball for the shot based on the determined distances and the determined angles;

determining an orientation and a position of the camera in three-dimensional (3-D) space based on the identified basketball hoop and the calculated trajectory; and

storing, in memory, calibration data indicative of the orientation and the position of the camera in 3-D space for use in tracking basketball shots by the computing device.

2. The method of claim 1 , wherein the computing device is a cellular telephone.

3. The method of claim 1 , wherein the determined distances are based on a resolution of the camera.

4. The method of claim 1 , wherein the determining the orientation of the camera is based on at least one accelerometer of the computing device.

5. The method of claim 1 , further comprising identifying at least one court marking of a basketball court for the basketball hoop, wherein the determining the orientation of the camera is based on the at least one court marking.

6. The method of claim 1 , further comprising identifying at least one backboard for the basketball hoop, wherein the determining the orientation of the camera is based on the backboard.

7. The method of claim 1 , further comprising:

determining a distance of the basketball hoop from the camera based on a length of a portion of the basketball hoop in at least one 2-D image captured by the camera; and

determining a location of a reference point in the 3-D space relative to the camera based on the calculated trajectory and the determined distance of the basketball hoop from the camera,

wherein the calibration data indicates the location of the reference point in the 3-D space relative to the camera.

8. A computing device, comprising:

a camera for capturing a plurality of two-dimensional (2-D) images of a shot of a basketball toward a basketball hoop;

at least one processor programmed with instructions that, when executed by the at least one processor, cause the at least one processor to:

identify the basketball in the plurality of 2-D images of the shot of the basketball;

identify the basketball hoop in the plurality of 2-D images of the shot of the basketball;

determine distances of the basketball from the camera based on sizes of the basketball in the plurality of 2-D images of the shot of the basketball;

determine angles of the basketball from the camera for of the plurality of 2-D images of the shot of the basketball based on positions of the basketball in the plurality of 2-D images of the shot of the basketball;

calculate a parabolic trajectory of the basketball for the shot based on the determined distances and the determined angles;

determine an orientation and a position of the camera in three-dimensional (3-D) space based on the identified basketball hoop and the calculated trajectory; and

store, in memory, calibration data indicative of the orientation and the position of the camera in 3-D space for use in tracking basketball shots by the computing device.

9. The computing device of claim 8 , wherein the computing device is a cellular telephone.

10. The computing device of claim 1 , wherein the determined distances are based on a resolution of the camera.

11. The computing device of claim 8 , wherein the instructions, when executed by the at least one processor, cause the at least one processor to determine the orientation of the camera based on at least one accelerometer of the computing device.

12. The computing device of claim 8 , wherein the instructions, when executed by the at least one processor, cause the at least one processor to:

identify at least one court marking of a basketball court for the basketball hoop; and

determine the orientation of the camera based on the at least one court marking.

13. The computing device of claim 8 , wherein the instructions, when executed by the at least one processor, cause the at least one processor to:

identify at least one backboard for the basketball hoop; and

determine the orientation of the camera is based on the backboard.

14. The computing device of claim 8 , wherein the instructions, when executed by the at least one processor, cause the at least one processor to:

determine a distance of the basketball hoop from the camera based on a length of a portion of the basketball hoop in at least one 2-D image captured by the camera; and

determine a location of a reference point in the 3-D space relative to the camera based on the calculated trajectory and the determined distance of the basketball hoop from the camera,

wherein the calibration data indicates the location of the reference point in the 3-D space relative to the camera.

Assignments (1)

Continuity (6)

References Cited (36)

Cited By (2)

US 12,423,834 US 12,718,384