Processing of geo-spatial athletics sensor data

• US 9,645,224 B2
• Filed: 03/19/2014
• Issued: 05/09/2017
• Est. Priority Date: 03/19/2014
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Abraham, Torsten, Foebel, Florian, Gruschko, Boris, Kazmaier, Gerrit Simon, Lahmer, Christian, Licht, Nico, Lieberenz, Marcus, Volker, Lars
• Primary Examiner(s): RENWICK, REGINALD A
• Application Number:
  US14/219,927
• Publication Number:
  US 20150265876A1
• Time in Patent Office: 1,147 Days
• CPC Class Codes: G01S 19/19 Sporting applications
• CPC Class Codes: G01S 5/0027 of actual mobile position, i.e. position determined on mobile

Abstract

Correlated and processed data is received that is derived from a plurality of geo-spatial sensors that respectively generate data characterizing a plurality of sources within a zone of interest. The data includes a series of time-stamped frames for each of the sensors. Subsequently, events of interest are identified, in real-time, based on relative positions of the sources within the zone of interest prior to the data being written to a data storage application. Data can then be provided (e.g., loaded, stored, displayed, transmitted, etc.), in real-time, that characterize the events of interest. Related apparatus, systems, techniques and articles are also described.

Claims

1. A method comprising:

receiving correlated and processed data derived from a plurality of geo-spatial sensors that respectively generate data characterizing a plurality of sources within a zone of interest, the data comprising a series of time-stamped frames for each of the sensors, and the plurality of sources including a ball;

detecting, in real-time, occurrences of one or more events of interest based on relative positions of the plurality of sources within the zone of interest, the detecting being performed prior to the data being written to a data storage application, the one or more events of interest including an attempt at a goal, and wherein the detecting of an attempt at the goal includes computing, based on the relative positions of the plurality of sources within the zone of interest, an offset between a trajectory of the ball and the goal; and

providing, in real-time, data characterizing the one or more events of interest.

2. A method as in claim 1, wherein the plurality of sources further comprises one or more athletes.

5. A method as in claim 1, wherein the one or more events of interest further include one or more goals.

6. A method as in claim 1, wherein the one or more events of interest further include one or more passes between a first player and a second player.

7. A method as in claim 6, wherein the one or more events of interest further include an interception of the ball from a first player from a first team by second a player from a second team.

8. A method as in claim 1, wherein the one or more events of interest further include a first player on a first team covering a second player on a second team.

9. A method as in claim 8, further comprising:

determining an outer boundary of coverage of the first player in relation to the second player.

10. A method as in claim 1, wherein the data storage application comprises an in-memory database.

11. A method as in claim 10, wherein the in-memory database comprises a columnar data store storing data in a columnwise-fashion.

12. A method as in claim 1, wherein the receiving, identifying, and processing, are implemented by at least one data processor forming part of at least one computing system.

13. A method as in claim 1, wherein an athletic event comprises the one or more events of interest.

14. A method as in claim 1, wherein an attempt at the goal is detected when the offset between the trajectory of the ball and the goal does not exceed a threshold value.

3. A method as in claim further comprising:

determining, based at least on a distance between the ball and the one or more athletes, that the ball is active.

4. A method as in claim 3, further comprising:

determining, based at least on an athlete of the one or more athletes that is closest to the ball, a team having possession of the ball.

15. A non-transitory computer program product storing instructions which, when executed by at least one data processor forming part of at least one computing system, result in operations comprising:

receiving correlated and processed data derived from a plurality of geo-spatial sensors that respectively generate data characterizing a plurality of sources within a zone of interest, the data comprising a series of time-stamped frames for each of the sensors, and the plurality of sources including a ball;

detecting, in real-time, occurrences of one or more events of interest based on relative positions of the plurality of sources within the zone of interest, the detecting being performed prior to the data being written to a data storage application, the one or more events of interest including an attempt at a goal, and wherein the detecting of an attempt at the goal includes computing, based on the relative positions of the plurality of sources within the zone of interest, an offset between a trajectory of the ball and the goal; and

providing, in real-time, data characterizing the one or more events of interest.

16. A computer program product as in claim 15, further comprising

determining, based at least on a distance between the ball and one or more athletes, that the ball is active;

and

determining, based at least on an athlete of the one or more athletes that is closest to the ball, a team having possession of the ball.

17. A computer program product as in claim 15, wherein the one or more events of interest further include one or more goals.

18. A system comprising:

an in-memory database comprising a columnar data store storing data in a columnwise-fashion;

at least one data processor; and

memory storing instructions which, when executed by the at least one data processor, result in operations comprising;

receiving correlated and processed data derived from a plurality of geo-spatial sensors that respectively generate data characterizing a plurality of sources within a zone of interest, the data comprising a series of time-stamped frames for each of the sensors, and the plurality of sources including a ball;

detecting, in real-time, occurrences of one or more events of interest based on relative positions of the plurality of sources within the zone of interest, the detecting being performed prior to the data being written to in-memory database, the one or more events of interest including an attempt at a goal, and wherein the detecting of an attempt at the goal includes computing, based on the relative positions of the plurality of sources within the zone of interest, an offset between a trajectory of the ball and the goal; and

providing, in real-time, data characterizing the events of interest.