Detection of kinetic events and mechanical variables from uncalibrated video
Systems and techniques are provided to identify, analyze, and evaluate key events and mechanical variables in videos of human motion related to an action, such as may be used in training for various sports and other activities. Information about the action is calculated based on analysis of the video such as via keypoint identification, pose identification and/or estimation, and related calculations, and provided automatically to the user to allow for improvement of the action.
1. A computer-implemented method comprising:
receiving an uncalibrated video showing performance of an action by a human subject;
extracting a plurality of two-dimensional (2D) poses of the human subject while performing the action based on an arrangement of keypoints on the human subject in one or more frames of the uncalibrated video, the keypoints comprising repeatably-identifiable points on the human subject, wherein the 2D poses comprise discrete arrangements of portions of the human subject relative to one another;
based upon the 2D poses, detecting one or more key events in the uncalibrated video, each of the key events corresponding to a predefined portion of the action corresponding to a specific temporal event occurring during performance of the action by the human subject;
based upon the key events, computing one or more mechanical variables of the human subject performing the action, the mechanical variables describing a physical arrangement of at least a part of the human subject performing the action; and
based upon the one or more mechanical variables, automatically providing information about performance of the action by the human subject, the information indicating at least one portion of the action that was performed sub-optimally by the human subject.
2. The method of claim 1 , wherein the plurality of 2D poses are selected from library of predefined two-dimensional (2D) signatures for the action based on the arrangement of keypoints.
3. The method of claim 2 , wherein each 2D signature in the library corresponds to a 2D projection of the action as seen from a corresponding point of view.
4. The method of claim 2 , wherein the 2D signatures are based upon a plurality of three-dimensional (3D) motion patterns previously obtained from 3D seed data.
5. The method of claim 4 , wherein the 3D seed data comprises motion capture data.
6. The method of claim 4 , wherein the 3D seed data comprises simulated motion data.
7. The method of claim 1 , further comprising:
prior to receiving the uncalibrated video, generating a library of predefined 2D signatures for the action based upon a plurality of 3D motion patterns obtained from 3D seed data.
8. The method of claim 1 , wherein the information further comprises an identification of one or more exercises, drills, or activities to perform to cause an improvement in the portion of the action that was performed sub-optimally by the human subject.
9. The method of claim 1 , wherein the action is a pitch by a baseball pitcher.
10. The method of claim 9 , wherein the key events comprise one or more selected from the group consisting of: a front foot lift, a max leg lift, a foot strike, a max hip and shoulder separation, shoulders squared up to target, and ball release.
11. A system comprising:
a processor configured to:
receive an uncalibrated video showing performance of an action by a human subject;
extract a plurality of two-dimensional (2D) poses of the human subject while performing the action based on an arrangement of keypoints on the human subject in one or more frames of the uncalibrated video, the keypoints comprising repeatably-identifiable points on the human subject, wherein the 2D poses comprise discrete arrangements of portions of the human subject relative to one another;
based upon the 2D poses, detect one or more key events in the uncalibrated video, each of the key events corresponding to a predefined portion of the action corresponding to a specific temporal event occurring during performance of the action by the human subject;
based upon the key events, compute one or more mechanical variables of the human subject performing the action, the mechanical variables describing a physical arrangement of at least a part of the human subject performing the action; and
based upon the one or more mechanical variables, automatically determine information about performance of the action by the human subject, the information indicating at least one portion of the action that was performed sub-optimally by the human subject; and
a user interface comprising a display, the interface capable of providing the information about the performance of the action by the human subject.
12. The system of claim 11 , wherein the plurality of 2D poses are selected from a library of predefined two-dimensional (2D) signatures for the action based on the arrangement of keypoints.
13. The system of claim 11 , further comprising a computerized video capture device configured to capture the uncalibrated video.
14. The system of claim 12 , wherein the video capture device comprises a phone or tablet with an integrated camera.
15. The system of claim 11 , wherein the information further comprises an identification of one or more exercises, drills, or activities to perform to cause an improvement in the portion of the action that was performed sub-optimally by the human subject.
16. The system of claim 11 , wherein the action is a pitch by a baseball pitcher.
17. A non-transitory computer-readable medium storing a plurality of instructions which, when executed by a processor, cause the processor to:
receive an uncalibrated video showing performance of an action by a human subject;
extract a plurality of two-dimensional (2D) poses of the human subject while performing the action based on an arrangement of keypoints on the human subject in one or more frames of the uncalibrated video, the keypoints comprising repeatably-identifiable points on the human subject, wherein, the 2D poses comprise discrete arrangements of portions of the human subject relative to one another;
based upon the 2D poses, detect one or more key events in the uncalibrated video, each of the key events corresponding to a predefined portion of the action corresponding to a specific temporal event occurring during performance of the action by the human subject;
based upon the key events, compute one or more mechanical variables of the human subject performing the action, the mechanical variables describing a physical arrangement of at least a part of the human subject performing the action; and
based upon the one or more mechanical variables, automatically determine information about performance of the action by the human subject, the information indicating at least one portion of the action that was performed sub-optimally by the human subject; and
display, on a user interface, the information about the performance of the action by the human subject.
18. The non-transitory computer-readable medium of claim 17 , wherein the plurality of 2D poses are selected from a library of predefined two-dimensional (2D) signatures for the action based on the arrangement of keypoints.
19. The system of claim 12 , wherein each 2D signature in the library corresponds to a 2D projection of the action as seen from a corresponding point of view.
20. The system of claim 12 , wherein the 2D signatures are based upon a plurality of three-dimensional (3D) motion patterns previously obtained from 3D seed data.
21. The system of claim 20 , wherein the 3D seed data comprises motion capture data.
22. The system of claim 20 , wherein the 3D seed data comprises simulated motion data.
23. The system of claim 11 , the processor further configured to:
generate a library of predefined 2D signatures for the action based upon a plurality of 3D motion patterns obtained from 3D seed data prior to receiving the uncalibrated video.
24. The system of claim 16 , wherein the key events comprise one or more selected from the group consisting of: a front foot lift, a max leg lift, a foot strike, a max hip and shoulder separation, shoulders squared up to target, and ball release.
25. The non-transitory computer-readable medium of claim 18 , wherein each 2D signature in the library corresponds to a 2D projection of the action as seen from a corresponding point of view.
26. The non-transitory computer-readable medium of claim 18 , wherein the 2D signatures are based upon a plurality of three-dimensional (3D) motion patterns previously obtained from 3D seed data.
27. The non-transitory computer-readable medium of claim 26 , wherein the 3D seed data comprises motion capture data.
28. The non-transitory computer-readable medium of claim 26 , wherein the 3D seed data comprises simulated motion data.
29. The non-transitory computer-readable medium of claim 17 , the instructions further causing the processor to:
generate a library of predefined 2D signatures for the action based upon a plurality of 3D motion patterns obtained from 3D seed data prior to receiving the uncalibrated video.
30. The non-transitory computer-readable medium of claim 17 , wherein the information further comprises an identification of one or more exercises, drills, or activities to perform to cause an improvement in the portion of the action that was performed sub-optimally by the human subject.
31. The non-transitory computer-readable medium of claim 17 , wherein the action is a pitch by a baseball pitcher.
32. The non-transitory computer-readable medium of claim 31 , wherein the key events comprise one or more selected from the group consisting of: a front foot lift, a max leg lift, a foot strike, a max hip and shoulder separation, shoulders squared up to target, and ball release.
33. The method of claim 1 , wherein the action is a golf swing.
34. The method of claim 33 , wherein the key events comprise one or more selected from the group consisting of: a peak of the golf swing between a backswing and a downswing, a moment of ball impact, an initial follow-through, and a final position.
35. The method of claim 1 , wherein the action is selected from a group consisting of: a boxing punch, a basketball freethrow, a hockey slapshot, and a tennis swing.
36. The system of claim 11 , wherein the action is a golf swing.
37. The system of claim 36 , wherein the key events comprise one or more selected from the group consisting of: a peak of the golf swing between a backswing and a downswing, a moment of ball impact, an initial follow-through, and a final position.
38. The system of claim 11 , wherein the action is selected from a group consisting of: a boxing punch, a basketball freethrow, a hockey slapshot, and a tennis swing.
39. The non-transitory computer-readable medium of claim 17 , wherein the action is a golf swing.
40. The non-transitory computer-readable of claim 39 , wherein the key events comprise one or more selected from the group consisting of: a peak of the golf swing between a backswing and a downswing, a moment of ball impact, an initial follow-through, and a final position.
41. The non-transitory computer-readable medium of claim 17 , wherein the action is selected from a group consisting of: a boxing punch, a basketball freethrow, a hockey slapshot, and a tennis swing.