Stereoscopic image capture with performance outcome prediction in sporting environments

• US 10,360,685 B2
• Filed: 05/27/2008
• Issued: 07/23/2019
• Est. Priority Date: 05/24/2007
• Status: Active Grant

• Current Assignee: Pillar Vision Incorporated
• Original Assignee: Pillar Vision Incorporated
• Inventors: Marty, Alan W., Edwards, Thomas A., Carter, John
• Primary Examiner(s): Liddle, Jay Trent
• Application Number:
  US12/127,744
• Publication Number:
  US 20080312010A1
• Time in Patent Office: 4,074 Days
• Field of Search: 2733173, 434248, 473416, 473422, 473447, 473448
• CPC Class Codes: A63B 2024/0034 during flight
• CPC Class Codes: A63B 2220/806 Video cameras
• CPC Class Codes: A63B 24/0003 Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis
• CPC Class Codes: A63B 24/0021 Tracking a path or terminating locations
• CPC Class Codes: A63B 69/00 Training appliances or apparatus for special sports training of parachutists B64D23/00
• CPC Class Codes: A63B 69/0071 for basketball
• CPC Class Codes: A63B 69/38 for tennis A63B61/006, A63B69/0073 and A63B69/0097 take precedence
• CPC Class Codes: A63B 71/0605 Decision makers and devices using detection means facilitating arbitration
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30224 Ball; Puck
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/285 using a sequence of stereo image pairs
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof
• CPC Class Codes: H04N 23/90 Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums

Abstract

Methods and apparatus relating to predicting outcome in a sporting environment are described. The methods and apparatus are used to relate trajectory performance of an object to body motions and body orientation associated with a generating the trajectory of the object. When equipment is utilized to generate the trajectory of an object, than the effects of equipment motions and equipment orientation can be also related to trajectory performance. The method and apparatus can be used to predict body motions and body orientations that increase the likelihood of achieving a desired outcome including specifying optimum motions and orientations for a particular individual. The method and apparatus may be used in training, coaching and broadcasting environments.

Claims

1. A method for basketball comprising:

capturing with at least one camera images of at least portions of a first plurality of actual basketball shots by an individual in sequences of video frames;

analyzing the images by at least one processor;

determining, by the at least one processor based on the analyzing, trajectories of a basketball from the sequences of video frames for the first plurality of actual basketball shots;

determining, by the at least one processor, at least one trajectory parameter for each of the first plurality of actual basketball shots from the trajectories determined for the first plurality of actual basketball shots;

determining, by the at least one processor across the first plurality of actual basketball shots, a variability of the at least one trajectory parameter determined from the trajectories;

determining, by the at least one processor, a range for the at least one trajectory parameter based on the variability determined by the at least one processor;

generating, by the at least one processor, a first plurality of simulated basketball shots based on the determined range, wherein for each of the first plurality of simulated basketball shots, the generating comprises;

(1) selecting a value for the at least one trajectory parameter within the determined range and (2) predicting whether a simulated basketball passes through a simulated basketball hoop based on the selected value for the at least one trajectory parameter; and

providing, by an interface, an output indicative of a skill level for the individual based on the predicting.

2. The method of claim 1, further comprising:

determining a percentage of made shots in the first plurality of simulated basketball shots.

3. The method of claim 1, wherein a number of the first plurality of simulated basketball shots generated is greater than 1000.

4. The method of claim 1, wherein a number of the first plurality of actual basketball shots is less than 100.

5. The method of claim 1, wherein a number of the first plurality of actual basketball shots is less than 50.

6. The method of claim 1, wherein the selected value for the at least one trajectory parameter is randomly selected within the determined range.

7. The method of claim 1, wherein the range is determined using a statistical analysis.

8. The method of claim 1, wherein the range is based upon at least a statistical mean of the at least one trajectory parameter and a deviation associated with the at least one trajectory parameter.

9. The method of claim 1, further comprising a second range for a second trajectory parameter from the trajectories determined for the first plurality of actual basketball shots, wherein the predicting is performed, for each of the first plurality of simulated basketball shots, using a second value within the second range of the second trajectory parameter.

10. The method of claim 9, wherein the second value is determined using a random number.

11. The method of claim 1, further comprising:

determining an optimum value of the at least one trajectory parameter;

determining a second range that includes the optimum value of the at least one trajectory parameter;

generating a second plurality of simulated basketball shots wherein each trajectory of the second plurality of simulated basketball shots is generated using a second value within the second range.

12. The method of claim 1, wherein the skill level is a shooting percentage for the user.

13. The method of claim 1, wherein the at least one trajectory parameter includes at least one of a group including:

a left to right position for the simulated basketball in a plane of the simulated basketball hoop, an entry angle for the simulated basketball into the simulated basketball hoop, and a front to back position for the simulated basketball in the plane of the simulated basketball hoop.

14. A method for basketball comprising:

capturing data with at least one camera, the data defining images of an individual shooting a plurality of basketball shots;

analyzing the images with the at least one processor;

determining, by the at least one processor from the analyzed images, at least one trajectory parameter for each of the plurality of basketball shots, the at least one trajectory parameter indicating a trajectory of a basketball for each of the plurality of basketball shots;

determining, by the at least one processor across the plurality of basketball shots, a variability of the at least one parameter;

generating a plurality of simulated basketball shots including (1) selecting, for each of the plurality of simulated basketball shots, a respective value for the at least one parameter based on the determined variability such that the values selected for the at least one parameter across the plurality of simulated basketball shots are within a range associated with the determined variability and (2) predicting, for each of the plurality of simulated basketball shots based on the;

selected value, whether a simulated basketball passes through a simulated basketball hoop;

predicting by the at least one processor a shooting percentage for the individual based on the generating; and

providing an output by an interface based on the predicted shooting percentage.

15. The method of claim 14, wherein a number of the plurality of basketball shots is less than 100.

16. The method of claim 14, wherein a number of the plurality of basketball shots is less than 50.

17. The method of claim 14, further comprising:

determining a maximum shooting percentage; and

relating the maximum shooting percentage to a body orientation associated with shooting a basketball.

18. The method of claim 17, wherein the body orientation is associated with a release angle of a basketball as it leaves a hand of the individual.

19. The method of claim 17, wherein the body orientation is associated with a release direction of a basketball as it leaves the hand of the individual.

20. The method of claim 14, further comprising determining a maximum shooting percentage;

and relating the maximum shooting percentage to a body motion.

21. The method of claim 20, wherein the body motion is associated with a movement of a hand of the individual.

22. The method of claim 20, wherein the body motion is associated with a movement of legs of the individual.

23. The method of claim 20, wherein the body motion is associated with a movement of arms of the individual.

24. The method of claim 20, wherein the body motion is associated with a movement of a joint of the individual.

25. The method of claim 14, further comprising:

generating an image showing shooting percentage as a function of a body orientation while shooting a basketball.

26. The method of claim 25, wherein the body orientation is associated with a release angle of the basketball as it leaves a hand of the individual.

27. The method of claim 25, wherein the body orientation is associated with a release direction of the basketball as it leaves a hand of the individual.

28. The method of claim 14, further comprising:

generating an image showing shooting percentage as a function of a body motion generated while shooting a basketball.

29. The method of claim 14, wherein the variability is determined using a statistical analysis.

30. The method of claim 14, wherein the determining the variability comprises determining a statistical mean of the at least one trajectory parameter and a deviation associated with the at least one trajectory parameter.

31. The method of claim 14, wherein the at least one trajectory parameter includes at least one of a group including:

left to right positions for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots, entry angles for the at least one basketball into the at least one basketball hoop, and a front to back position for the at least one basketball in the plane of the at least one basketball hoop.

32. The method claim 14, further comprising comparing the variability to a variability associated with a plurality of individuals shooting basketball shots or making motions associated with shooting basketball shots, wherein the predicting the shooting percentage is based on the comparing.

33. A method for basketball, said method comprising:

capturing data with at least one camera, the data defining images of an individual shooting or making motions associated with shooting a plurality of basketball shots;

analyzing the images by at least one processor;

determining, by the at least one processor from the analyzed images, at least one parameter for each of the plurality of basketball shots, the at least one parameter indicating body motions of the individual, body orientations of the individual, trajectories of the plurality of basketball shots or combinations thereof;

determining, by the at least one processor, a variability of the at least one parameter across the plurality of basketball shots;

generating by the at least one processor a plurality of simulated basketball shots including determining for each of the simulated basketball shots a respective value for the at least one parameter based on the determined variability such that the values determined, by the at least one processor, for the at least one parameter across the plurality of simulated basketball shots are within a range associated with the determined variability,

predicting by the at least one processor outcomes to the plurality of simulated basketball shots including determining for each of the plurality of simulated basketball shots whether a simulated basketball passes through a simulated basketball hoop based on the respective value determined for the simulated basketball shot; and

providing, by an interface, an output indicative of a skill level for the individual based on the predicted outcomes.

34. The method of claim 33, wherein the at least one parameter includes at least one of a group including:

positions for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots and entry angles for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots.

35. The method of claim 33, wherein the skill level is a shooting percentage for the individual.

36. The method of claim 33, wherein the at least one parameter includes left to right positions for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots.

37. The method of claim 33, wherein the at least one parameter includes entry angles for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots.

38. The method of claim 33, wherein the at least one parameter includes front to back positions for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots.

39. The method of claim 33, wherein the at least one parameter includes at least one of a group including:

positions for at least one basketball in a plane of at least one basketball hoop for the plurality of actual basketball shots and entry angles for at least one basketball in a plane of at least one basketball hoop for the plurality of basketball shots.

40. The method of claim 33, further comprising:

determining a maximum shooting percentage; and

relating the maximum shooting percentage to a body orientation or a body motion associated with shooting a basketball.

41. The method of claim 40, wherein the body motion is associated with a movement of a hand of the individual.

42. The method of claim 33, further comprising:

generating an image showing shooting percentage as a function of a body orientation or body motion while shooting a basketball.

43. A method for basketball comprising:

capturing data with at least one camera, the data defining images of an individual shooting a plurality of actual basketball shots or making motions associated with shooting a plurality of basketball shots;

analyzing the images with at least one processor;

measuring, by the at least one processor based on the analyzing, at least one parameter for each of (1) the plurality of actual basketball shots or (2) the motions associated with shooting the plurality of basketball shots, wherein the at least one parameter includes at least one of the group including;

a parameter indicating motion of a body part of the individual and a parameter indicating a basketball trajectory;

determining, by the at least one processor based on the measuring, a variability of the at least one parameter across the plurality of actual basketball shots or the motions associated with shooting a plurality of basketball shots;

determining, by the at least one processor, a range for the at least one parameter based on the variability;

generating, by the at least one processor, a plurality of basketball shot simulations, wherein the generating comprises selecting, by the at least one processor based on the determined range, values for the at least one parameter within the determined range for the plurality of basketball shot simulations, and wherein the generating comprises determining a trajectory for each of the plurality of basketball shot simulations based on a respective one of the selected values;

predicting, by the at least one processor, a skill level for the individual based on the plurality of basketball shot simulations generated by the at least one processor including determining for each of the plurality of basketball shot simulations whether a simulated basketball passes through a simulated basketball hoop; and

providing an output indicative of the predicted skill level by an interface.

44. The method of claim 43, further comprising storing information related to the data to a database, wherein the database allows queries based upon identification information associated with the individual.

45. The method of claim 43, further comprising:

identifying in the data a location on a body of the individual; and

determining one or more changes of position of the location.

46. The method of claim 43, wherein a value associated with a body motion is randomly determined and wherein the value is used in at least one of the basketball shot simulations.

47. The method of claim 43, wherein the skill level is a shooting percentage for the individual.

48. The method of claim 43, wherein the at least one parameter includes left to right positions for at least one basketball in a plane of at least one basketball hoop for the plurality of actual basketball shots.

49. The method of claim 43, wherein the at least one parameter includes entry angles for at least one basketball in a plane of at least one basketball hoop for the plurality of actual basketball shots.

50. The method of claim 43, wherein the at least one parameter includes front to back positions for at least one basketball in a plane of at least one basketball hoop for the plurality of actual basketball shots.

51. The method of claim 43, wherein the at least one parameter includes at least one of a group including:

positions for at least one basketball in a plane of at least one basketball hoop for the plurality of actual basketball shots and entry angles for at least one basketball in a plane of at least one basketball hoop for the plurality of actual basketball shots.

52. A non-transitory computer readable medium for tangibly storing a computer program for a computer, the computer program executed by at least one processor to generate a method for basketball, the computer readable medium comprising:

computer code for receiving data defining images of an individual shooting a plurality of basketball shots;

computer code for analyzing the images to determine at least one trajectory parameter for each of the plurality of basketball shots, the at least one trajectory parameter indicating a trajectory of a basketball for each of the plurality of basketball shots;

computer code for determining, across the plurality of basketball shots, a variability of the at least one parameter;

computer code for generating a plurality of simulated basketball shots based on the variability including (1) selecting, for each of the plurality of simulated basketball shots, a respective value for the at least one parameter based on the determined variability such that the values selected for the at least one parameter across the plurality of simulated basketball shots are within a range associated with the determined variability and (2) predicting, for each of the plurality of simulated basketball shots based on the selected value, whether a simulated basketball passes through a simulated basketball hoop;

computer code for predicting a shooting percentage for the individual based on the computer code for generating; and

computer code for providing an output based on the predicted shooting percentage.

53. A non-transitory computer readable medium for tangibly storing a computer program for a computer, the computer program executed by at least one processor on the computer to generate a method for basketball, the computer readable medium comprising:

computer code for receiving data defining images of an individual shooting a plurality of actual basketball shots or making motions associated with shooting a plurality of basketball shots;

computer code for analyzing the images to measure at least one parameter for each of the plurality of basketball shots, the at least one parameter indicating body motions of the individual, body orientations of the individual, trajectories of the plurality of basketball shots or combinations thereof;

computer code for determining a variability of the at least one parameter across the plurality of basketball shots based on measurements by the computer code for analyzing the images;

computer code for generating a plurality of simulated basketball shots based on the variability including determining for each of the simulated basketball shots a respective value for the at least one parameter based on the determined variability such that the values determined, by the computer code for generating, for the at least one parameter across the plurality of simulated basketball shots are within a range associated with the determined variability;

computer code for predicting outcomes to the plurality of simulated basketball shots including determining for each of the plurality of simulated basketball shots whether a simulated basketball passes through a simulated basketball hoop based on the respective value; and

computer code for providing an output indicative of a skill level for the individual based on the predicted outcomes.