Systems and methods for identifying and characterizing athletic maneuvers

• US 10,548,514 B2
• Filed: 07/01/2013
• Issued: 02/04/2020
• Est. Priority Date: 03/07/2013
• Status: Active Grant

• Current Assignee: AlpineReplay, Inc.
• Original Assignee: AlpineReplay, Inc.
• Inventors: Lokshin, Anatole M., Kuzkin, Vitaly A.
• Primary Examiner(s): Betsch, Regis J
• Assistant Examiner(s): Knox, Kaleria
• Application Number:
  US13/932,899
• Publication Number:
  US 20140257743A1
• Time in Patent Office: 2,409 Days
• Field of Search: 702141, 702727, 702104, 702 19, 473570, 473199, 473223, 473422, 473247, 600409, 382168, 482 1, 3405731, 707727, 706 2, 434252, 700 90
• CPC Class Codes: A61B 2503/10 Athletes
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/1122 of movement trajectories
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: G01S 19/19 Sporting applications
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations

Abstract

Embodiments of the present disclosure help automatically identify athletic maneuvers performed by actors and/or their sports equipment using data from sensors. Among other things, various embodiments help judges and spectators of extreme sports to assess athletic maneuvers based on objective, empirical data and allow action sport participants to objectively compare tricks performed at different times and/or different locations. A computer-implemented method according to one embodiment of the present disclosure comprises receiving, by a computer system, sensor data related to motion by an actor over a time period; determining, by the computer system and based on the sensor data, a plurality of motion characteristics; and identifying, based on the plurality of motion characteristics, an athletic maneuver associated with the motion by the actor during the time period.

Claims

1. A computer-implemented method comprising:

receiving, by a computer system, sensor data related to motion by an actor over a time period;

determining a local vertical vector for the actor for use in determining an angle of self-rotation for the actor and an angle of flip for the actor, the determining the local vertical vector based on sensor data from one or more magnetometers;

determining, by the computer system and based on the sensor data, a plurality of motion characteristics including determining the angle of self-rotation for the actor and determining the angle of flip for the actor,

wherein determining the angle of self-rotation for the actor includes;

calculating a plurality of unit vectors orthogonal to the local vertical vector for the actor;

calculating a plurality of angles determining rotation of the unit vectors around the local vertical vector; and

selecting the angle of self-rotation for the actor as a maximum angle from the plurality of angles;

receiving a plurality of athletic maneuver definitions, wherein each athletic maneuver definition comprises a set of motion characteristics associated with athletic maneuvers;

identifying an athletic maneuver definition from the plurality of athletic maneuver definitions, wherein identifying an athletic maneuver definition from the plurality of athletic maneuver definitions comprises selecting an athletic maneuver definition having a set of motion characteristics that includes the determined angle of self-rotation for the actor and the determined angle of flip for the actor; and

overlaying information related to the athletic maneuver on video of the actor performing the athletic maneuver, wherein the information related to the athletic maneuver is at least based on the determined angle of self-rotation for the actor and the determined angle of flip for the actor.

2. The method of claim 1, wherein the plurality of motion characteristics includes one or more of:

position;

velocity;

acceleration;

orientation;

rotation; and

translation.

3. The method of claim 1, wherein the sensor data includes data from one or more of:

an accelerometer;

a gyroscope;

a magnetometer;

a Hall effect sensor;

a global positioning system;

an ultrasonic sensor; and

an optical sensor.

4. The method of claim 1, wherein at least one of the plurality of motion characteristics is determined relative to one or more axis of an absolute frame of reference that is independent of the actor, and wherein at least one other of the plurality of motion characteristics is determined relative to one or more axis of a local frame of reference that is associated with the actor.

5. The method of claim 1, wherein determining the plurality of motion characteristics includes determining an orientation for the actor at the beginning of the time period.

6. The method of claim 1, wherein determining the plurality of motion characteristics includes determining a facing for the actor based on a direction of a velocity vector calculated from the sensor data and a direction of a magnetic vector calculated using information from a magnetometer sensor in the sensor data.

7. The method of claim 1, wherein identifying the athletic maneuver includes comparing the plurality of determined motion characteristics to one or more motion characteristics associated with a known athletic maneuver.

8. The method of claim 1, further comprising:

determining the quality of the determined motion characteristics, wherein the quality of the determined motion characteristics is determined based on a level of similarity between each of the determined motion characteristics and each of the motion characteristics associated with the identified athletic maneuver; and

generating an alert in response to the level of similarity being beneath a predetermined threshold.

9. The method of claim 7, wherein the one or more motion characteristics associated with the known athletic maneuver includes one or more of:

an orientation of the actor at a start of the time period;

an angle of rotation around a local axis of the actor;

a direction of rotation of the actor around a local axis of the actor;

an angle of rotation around an absolute axis perpendicular to a plane of motion of the actor;

a direction of rotation round an absolute axis perpendicular to a plane of motion of the actor; and

a leading edge of a piece of sports equipment at a start of the time period.

10. The method of claim 7, wherein the known athletic maneuver is stored in the database with one or more associated motion characteristics.

13. The method of claim 1, wherein the time period is measured from a global positioning system, based on a signal from a gyroscope or based on fuzzy logic analysis of one or more sensor signals.

14. The method of claim 1, wherein the determining the local vertical vector is further based on one or more of:

an average of sensor data from one or more accelerometers prior to an athletic maneuver that occurs during the time period;

an average of sensor data from one or more accelerometers after the athletic maneuver; and

sensor data from one or more accelerometers associated with a portion of the athletic maneuver.

15. The method of claim 14, wherein determining the angle of flip for the actor includes:

determining motion of the local vertical vector, associated with the actor, in a global frame of reference;

identifying a plane of movement for the vertical unit vector based of the motion of the local vertical vector;

calculating a projection of the local vertical vector on the plane; and

selecting the angle of flip for the actor as the angle of an arc segment traveled by the projection on the plane.

16. The method of claim 1, wherein determining the angle of flip for the actor includes:

determining motion of the local vertical vector, associated with the actor, in a global frame of reference;

identifying a plane of movement for the vertical unit vector based of the motion of the local vertical vector;

calculating a projection of the local vertical vector on the plane; and

selecting the angle of flip for the actor as the angle of an arc segment traveled by the projection on the plane.

11. A non-transitory, computer-readable medium storing instructions that, when executed, cause a computing device to:

receive sensor data related to motion by an actor over a time period;

determine a local vertical vector for the actor for use in determining an angle of self-rotation for the actor and an angle of flip for the actor, the determining the local vertical vector based on sensor data from one or more magnetometers;

determine, based on the sensor data, a plurality of motion characteristics including determining the angle of self-rotation for the actor and determining the angle of flip for the actor,

wherein determining the angle of self-rotation for the actor includes;

calculating a plurality of unit vectors orthogonal to the local vertical vector for the actor;

calculating a plurality of angles determining rotation of the unit vectors around the local vertical vector; and

selecting the angle of self-rotation for the actor as a maximum angle from the plurality of angles;

receive a plurality of athletic maneuver definitions, wherein each athletic maneuver definition comprises a set of motion characteristics associated with athletic maneuvers;

identify an athletic maneuver definition from the plurality of athletic maneuver definitions, wherein identifying an athletic maneuver definition from the plurality of athletic maneuver definitions comprises selecting an athletic maneuver definition having a set of motion characteristics that includes the determined angle of self-rotation for the actor and the determined angle of flip for the actor; and

overlay information related to the athletic maneuver on video of the actor performing the athletic maneuver, wherein the information related to the athletic maneuver is at least based on the determined angle of self-rotation for the actor and the determined angle of flip for the actor.

17. The non-transitory computer-readable medium of claim 11, wherein the determining the local vertical vector is further based on one or more of:

an average of sensor data from one or more accelerometers prior to an athletic maneuver that occurs during the time period;

an average of sensor data from one or more accelerometers after the athletic maneuver; and

sensor data from one or more accelerometers associated with a portion of the athletic maneuver.

18. The non-transitory computer-readable medium of claim 17, wherein determining the angle of flip for the actor includes:

determining motion of the local vertical vector, associated with the actor, in a global frame of reference;

identifying a plane of movement for the vertical unit vector based of the motion of the local vertical vector;

calculating a projection of the local vertical vector on the plane; and

selecting the angle of flip for the actor as the angle of an arc segment traveled by the projection on the plane.

12. A system comprising:

at least one processor; and

memory in communication with the at least one processor and storing instructions that, when executed by the processor, cause the system to;

receive sensor data related to motion by an actor over a time period;

determine a local vertical vector for the actor for use in determining an angle of self-rotation for the actor and an angle of flip for the actor, the determining the local vertical vector based on sensor data from one or more magnetometers;

determine, based on the sensor data, a plurality of motion characteristics including determining the angle of self-rotation for the actor and determining the angle of flip for the actor,

wherein determining the angle of self-rotation for the actor includes;

calculating a plurality of unit vectors orthogonal to the local vertical vector for the actor;

calculating a plurality of angles determining rotation of the unit vectors around the local vertical vector; and

selecting the angle of self-rotation for the actor as a maximum angle from the plurality of angles;

receive a plurality of athletic maneuver definitions, wherein each athletic maneuver definition comprises a set of motion characteristics associated with athletic maneuvers;

identify an athletic maneuver definition from the plurality of athletic maneuver definitions, wherein identifying an athletic maneuver definition from the plurality of athletic maneuver definitions comprises selecting an athletic maneuver definition having a set of motion characteristics that includes the determined angle of self-rotation for the actor and the determined angle of flip for the actor; and

overlay information related to the athletic maneuver on video of the actor performing the athletic maneuver, wherein the information related to the athletic maneuver is at least based on the determined angle of self-rotation for the actor and the determined angle of flip for the actor.

19. The system of claim 12, wherein the determining the local vertical vector is further based on one or more of:

an average of sensor data from one or more accelerometers prior to an athletic maneuver that occurs during the time period;

an average of sensor data from one or more accelerometers after the athletic maneuver; and

sensor data from one or more accelerometers associated with a portion of the athletic maneuver.

20. The system of claim 19, wherein determining the angle of flip for the actor includes:

determining motion of the local vertical vector, associated with the actor, in a global frame of reference;

identifying a plane of movement for the vertical unit vector based of the motion of the local vertical vector;

calculating a projection of the local vertical vector on the plane; and

selecting the angle of flip for the actor as the angle of an arc segment traveled by the projection on the plane.