Classification of activity derived from multiple locations

• US 10,372,992 B2
• Filed: 06/07/2018
• Issued: 08/06/2019
• Est. Priority Date: 11/08/2013
• Status: Active Grant

• Current Assignee: 24 Invincibles Limited
• Original Assignee: Performance Lab Technologies Ltd (Pear Sports, LLC)
• Inventors: Ackland, Jonathan Edward Bell, Nayler, Mark
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US16/002,271
• Publication Number:
  US 20180314895A1
• Time in Patent Office: 425 Days
• Field of Search: 382103, 348169, 348157
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 20/42 of sport video content

Abstract

The invention provides a method of analyzing a sporting activity comprising receiving location data associated with a first player, a second player, and a game object; detecting, by a processing device, a game event associated with the first player; determining, in view of the received location data, a plurality of relative locations of the first player at a time prior to the game event, wherein the plurality of relative locations comprise a relative location in relation to the second player and a relative location in relation to a playing area; and classifying the game event based on the plurality of relative locations of the first player at the time prior to the game event.

Claims

1. A method of analyzing a sporting activity comprising:

receiving location data associated with a first player, a second player, and a game object, wherein the location data is derived from one or more sensor devices;

detecting, by a computer comprising one or more processors, a game event associated with the first player;

determining, in view of the received location data, a plurality of relative locations of the first player at a time prior to the game event, wherein the plurality of relative locations comprise a relative location in relation to the second player and a relative location in relation to a playing area; and

classifying, by the computer comprising the one or more processors, the game event based on the plurality of relative locations of the first player at the time prior to the game event.

2. The method of claim 1, wherein detecting the game event comprises detecting at least one of a goal, an assist, a pass, a possession change, an off side infraction, or a game object exceeding a boundary of the playing area.

3. The method of claim 1, wherein detecting the game event comprises detecting the game event based on the location data associated with the game object and location data associated with a scoring area.

4. The method of claim 1, wherein the first player comprises an offensive player and the second player comprises a defensive player, and wherein determining the relative location in relation to the second player comprises calculating a geo spatial relationship between the offensive player and the defensive player.

5. The method of claim 4, further comprising detecting that the offensive player is closer to a scoring area than the defensive player, and wherein the relative location of the offensive player in relation to the defensive player exceeds a predetermined threshold distance.

6. The method of claim 4, further comprising detecting that the defensive player is closer to a scoring area than the offensive player, and wherein the relative location of the offensive player in relation to the location of the defensive player is within a predetermined threshold distance.

7. The method of claim 4, further comprising:

detecting a pass to the offensive player, the pass occurring prior to the game event;

determining the offensive player at the time of the pass is closer to a scoring area than an average distance from the scoring area of a plurality of defensive players; and

further classifying the game event based on the detected pass and on the determining the offensive player is closer.

8. The method of claim 4, further comprising:

detecting a first game event comprising a first pass to a second offensive player, the first pass occurring at a first time prior to the game event;

detecting a second game event comprising a second pass from the second offensive player to the offensive player, the second pass occurring at a second time prior to the game event;

determining the second offensive player is at least a predetermined threshold distance away from all defensive players between the first time and the second time; and

further classifying the game event associated with the offensive player based on the detected first game event and second game event.

9. The method of claim 4, further comprising:

detecting the defensive player is closer to a second offensive player than all other defensive players;

determining the defensive player is moving away from the scoring area at the time of the game event associated with the first player, wherein the game event comprises a goal; and

further classifying the game event based on the determined defensive player moving away from the scoring area.

10. The method of claim 4, further comprising:

determining the offensive player possesses a game object for a time period exceeding a predetermined threshold duration; and

detecting a plurality of defensive players are within a predetermined threshold distance from the offensive player during the time period.

11. The method of claim 1, wherein the classifying comprises classifying the game event as a first game event based on the first player being within a penalty box and outside a goal box.

12. The method of claim 1, wherein the classifying comprises classifying the game event as a second game event based on the first player being within a penalty box and within a goal box.

13. The method of claim 1, further comprising determining a relative location between the first player and a game object and a relative location between the second player and the game object.

14. The method of claim 1, further comprising transmitting an alert to a user, the alert corresponding to the first player and being based on at least one of the plurality of relative locations.

15. The method of claim 1, further comprising:

detecting a pass to the first player from a third player, the pass occurring prior to the game event;

determining the first player is closer to a scoring area than the third player at the time of the pass; and

further classifying the game event based on the detected pass from the third player and on the determining the first player is closer.

16. The method of claim 1, further comprising:

detecting a pass to the first player from a third player, the pass occurring prior to the game event;

determining the first player is further from a scoring area than the third player at the time of the pass; and

further classifying the game event based on the detected pass from the third player and on the determining the first player is further.

17. A non-transitory machine-readable storage medium comprising instructions that cause a computer comprising one or more processors to:

receive location data associated with a first player, a second player, and a game object, wherein the location data is derived from one or more sensor devices;

detect a game event associated with the first player;

determine, in view of the received location data, a plurality of relative locations of the first player at a time prior to the game event, wherein the plurality of relative locations comprise a relative location in relation to the second player and a relative location in relation to a playing area; and

classify the game event based on the plurality of relative locations of the first player at the time prior to the game event.

18. The non-transitory machine-readable storage medium of claim 17, wherein to detect the game event the one or more processors are to detect at least one of a goal, an assist, a pass, a possession change, an off side infraction, or a game object exceeding a boundary of the playing area.

19. The non-transitory machine-readable storage medium of claim 17, wherein the first player comprises an offensive player and the second player comprises a defensive player, and wherein to determine the relative location in relation to the second player the one or more processors are to calculate a geo spatial relationship between the offensive player and the defensive player.

20. The non-transitory machine-readable storage medium of claim 19, wherein the one or more processors are further to detect that the offensive player is closer to a scoring area than the defensive player, and wherein the relative location of the offensive player in relation to the defensive player exceeds a predetermined threshold distance.

21. The non-transitory machine-readable storage medium of claim 19, wherein the one or more processors are further to:

detect a pass to the offensive player, the pass occurring prior to the game event;

determine the offensive player at the time of the pass is closer to a scoring area than an average distance from the scoring area of a plurality of defensive players; and

further classify the game event based on the detected pass and on the determining the offensive player is closer.

22. The non-transitory machine-readable storage medium of claim 19, wherein the one or more processors are further to:

detect a first game event comprising a first pass to a second offensive player, the first pass occurring at a first time prior to the game event;

detect a second game event comprising a second pass from the second offensive player to the offensive player, the second pass occurring at a second time prior to the game event;

determine the second offensive player is at least a predetermined threshold distance away from all defensive players between the first time and the second time; and

further classify the game event associated with the offensive player based on the detected first game event and second game event.

23. The non-transitory machine-readable storage medium of claim 19, wherein the one or more processors are further to:

detect the defensive player is closer to a second offensive player than all other defensive players;

determine the defensive player is moving away from the scoring area at the time of the game event associated with the first player, wherein the game event comprises a goal; and

further classify the game event based on the determined defensive player moving away from the scoring area.

24. The non-transitory machine-readable storage medium of claim 19, wherein the one or more processors are further to:

determine the offensive player possesses a game object for a time period exceeding a predetermined threshold duration; and

detect a plurality of defensive players are within a predetermined threshold distance from the offensive player during the time period.

25. The non-transitory machine-readable storage medium of claim 17, wherein to classify the game event the one or more processors are to classify the game event as a first game event based on the first player being within a penalty box and outside a goal box.

26. The non-transitory machine-readable storage medium of claim 17, wherein the one or more processors are further to transmit an alert to a user, the alert corresponding to the first player and being based on at least one of the plurality of relative locations.

27. The non-transitory machine-readable storage medium of claim 17, wherein the one or more processors are further to:

detect a pass to the first player from a third player, the pass occurring prior to the game event;

determine the first player is closer to a scoring area than the third player at the time of the pass; and

further classify the game event based on the detected pass from the third player and on the determining the first player is closer.

28. The non-transitory machine-readable storage medium of claim 17, wherein the one or more processors are further to:

detect a pass to the first player from a third player, the pass occurring prior to the game event;

determine the first player is further from a scoring area than the third player at the time of the pass; and

further classify the game event based on the detected pass from the third player and on the determining the first player is further.

29. A computer system comprising:

a memory; and

one or more processors communicably coupled to the memory, the one or more processors to;

receive location data associated with a first player, a second player, and a game object, wherein the location data is derived from one or more sensor devices;

detect, by the one or more processors, a game event associated with the first player;

determine, in view of the received location data, a plurality of relative locations of the first player at a time prior to the game event, wherein the plurality of relative locations comprise a relative location in relation to the second player and a relative location in relation to a playing area; and

classify the game event based on the plurality of relative locations of the first player at the time prior to the game event.