PERSONALIZING PREDICTION OF PERFORMANCE USING DATA AND BODY-POSE FOR ANALYSIS OF SPORTING PERFORMANCE
A method of generating a player prediction is disclosed herein. A computing system retrieves data from a data store. The computing system generates a predictive model using an artificial neural network. The artificial neural network generates one or more personalized embeddings that include player-specific information based on historical performance. The computing system selects, from the data, one or more features related to each shot attempt captured in the data. The artificial neural network learns an outcome of each shot attempt based at least on the one or more personalized embeddings and the one or more features related to each shot attempt.
1 . A method comprising:
receiving, by a processor of a computing system, real-time tracking data from a tracking system for a sporting event between a first team and a second team,
wherein the tracking system comprises an optically-based system using one or more cameras, and wherein the tracking system records motion of one or more players or one or more objects associated with the sporting event;
identifying, by the processor of the computing system, a scoring attempt event in the real-time tracking data for the sporting event;
determining, by the computing system, a set of players involved in the scoring attempt event, the set of players comprising a defensive player defending the scoring attempt event and an offensive player initiating the scoring attempt event;
extracting, by the processor of the computing system, one or more features related to the scoring attempt event, the one or more features comprising body pose information of the offensive player;
predicting, by the processor of the computing system, a likely outcome of the scoring attempt event based on the one or more features related to the scoring attempt event; and
outputting, by the processor of the computing system, a graphical representation of the likely outcome of the scoring attempt for visual depiction via a display.
2 . The method of claim 1 , wherein extracting, by the computing system, the one or more features related to the scoring attempt event comprises:
identifying one or more geometric features corresponding to the scoring attempt event based on the one or more features, the one or more geometric features comprising one or more of an angle between the offensive player and the defensive player, a first distance from the offensive player to a center of a goal, or a second distance from the defensive player to the center of the goal.
3 . The method of claim 1 , wherein extracting, by the computing system, the one or more features related to the scoring attempt event comprises:
identifying the body pose information of the offensive player initiating the scoring attempt event based on the one or more features, wherein the body pose information includes offensive player start position, angle, run type, or shot initiation.
4 . The method of claim 1 , further comprising:
identifying, by the computing system, a second defensive player; and
predicting, by the computing system, a second likely outcome of the scoring attempt event by replacing the defensive player with the second defensive player.
5 . The method of claim 4 , further comprising:
generating, by the computing system, a graphical representation comparing the likely outcome of the scoring attempt event with the defensive player to the second likely outcome of the scoring attempt event with the second defensive player.
6 . The method of claim 1 , further comprising:
identifying, by the computing system, a second offensive player; and
predicting, by the computing system, a second likely outcome of the scoring attempt event by replacing the offensive player with the second offensive player.
7 . The method of claim 6 , further comprising:
generating, by the computing system, a graphical representation comparing the likely outcome of the scoring attempt event with the offensive player to the second likely outcome of the scoring attempt event with the second offensive player.
8 . A non-transitory computer readable medium comprising one or more sequences of instructions, which, when executed by a processor, causes a computing system to perform operations comprising:
receiving, by the processor of the computing system, real-time tracking data from_a tracking system for a sporting event between a first team and a second team;
identifying, by the computing system, a scoring attempt event in the tracking data for the sporting event, wherein the tracking system comprises an optically-based system using one or more cameras, and wherein the tracking system records motion of one or more players or one or more objects associated with the sporting event;
determining, by the processor of the computing system, a set of players involved in the scoring attempt event, the set of players comprising a defensive player defending the scoring attempt event and an offensive player initiating the scoring attempt event;
extracting, by the processor of the computing system, one or more features related to the scoring attempt event, the one or more features comprising body pose information of the offensive player;
predicting, by the processor of the computing system, a likely outcome of the scoring attempt event based the one or more features related to the scoring attempt event; and
outputting, by the processor of the computing system, a graphical representation of the likely outcome of the scoring attempt for visual depiction via a display.
9 . The non-transitory computer readable medium of claim 8 , wherein extracting, by the computing system, the one or more features related to the scoring attempt event comprises:
identifying one or more geometric features corresponding to the scoring attempt event based on the one or more features, the one or more geometric features comprising one or more of an angle between the offensive player and the defensive player, a first distance from the offensive player to a center of a goal, or a second distance from the defensive player to the center of the goal.
10 . The non-transitory computer readable medium of claim 8 , wherein extracting, by the computing system, the one or more features related to the scoring attempt event comprises:
identifying the body pose information of the offensive player initiating the scoring attempt event based on the one or more features, wherein the body pose information includes offensive player start position, angle, run type, or shot initiation.
11 . The non-transitory computer readable medium of claim 8 , further comprising:
identifying, by the computing system, a second defensive player; and
predicting, by the computing system, a second likely outcome of the scoring attempt event by replacing the defensive player with the second defensive player.
12 . The non-transitory computer readable medium of claim 11 , further comprising:
generating, by the computing system, a graphical representation comparing the likely outcome of the scoring attempt event with the defensive player to the second likely outcome of the scoring attempt event with the second defensive player.
13 . The non-transitory computer readable medium of claim 8 , further comprising:
identifying, by the computing system, a second offensive player; and
predicting, by the computing system, a second likely outcome of the scoring attempt event by replacing the offensive player with the second offensive player.
14 . The non-transitory computer readable medium of claim 13 , further comprising:
generating, by the computing system, a graphical representation comparing the likely outcome of the scoring attempt event with the offensive player to the second likely outcome of the scoring attempt event with the second offensive player.
15 . A system comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations comprising:
receiving real-time tracking data from a tracking system for a sporting event between a first team and a second team,
wherein the tracking system comprises:
an optically-based system using one or more cameras, and
wherein the tracking system records motion of one or more players or one or more objects associated with the sporting event;
identifying a scoring attempt event in the real-time tracking data for the sporting event;
determining a set of players involved in the scoring attempt event, the set of players comprising a defensive player defending the scoring attempt event and an offensive player initiating the scoring attempt event;
extracting one or more features related to the scoring attempt event, the one or more features comprising body pose information of the offensive player;
predicting a likely outcome of the scoring attempt event based the scoring attempt event; and
outputting a graphical representation of the likely outcome of the scoring attempt for visual depiction via a display.
16 . The system of claim 15 , wherein extracting the one or more features related to the scoring attempt event comprises:
identifying one or more geometric features corresponding to the scoring attempt event based on the one or more features, the one or more geometric features comprising one or more of an angle between the offensive player and the defensive player, a first distance from the offensive player to a center of a goal, or a second distance from the defensive player to the center of the goal.
17 . The system of claim 15 , wherein extracting the one or more features related to the scoring attempt event comprises:
identifying the body pose information of the offensive player initiating the scoring attempt event based on the one or more features, wherein the body pose information includes offensive player start position, angle, run type, or shot initiation.
18 . The system of claim 15 , wherein the operations further comprise:
identifying a second defensive player; and
predicting a second likely outcome of the scoring attempt event by replacing the defensive player with the second defensive player.
19 . The system of claim 18 , wherein the operations further comprise:
generating a graphical representation comparing the likely outcome of the scoring attempt event with the defensive player to the second likely outcome of the scoring attempt event with the second defensive player.
20 . The system of claim 15 , wherein the operations further comprise:
identifying a second offensive player; and
predicting a second likely outcome of the scoring attempt event by replacing the offensive player with the second offensive player.