Granted Patent B2

US 12,725,416 · App. 18/107,939 · Granted Sep 1, 2026

Inventors: Samuel Green (Basingstoke, GB); Raymond Tang (Basingstoke, GB)

Assignees: SONY EUROPE BV; SONY GROUP CORPORATION

G06V20/42G06T7/70G06V20/47G06T2207/10016G06T2207/30224

Abstract

Claims (45)

1 . A method for generating a sports game highlight video based on winning probability, comprising the steps of:

receiving video of the sports game from at least one image capture device;

performing object tracking analysis on the video to generate tracking data providing ball trajectory and player position information;

identifying a plurality of shot events in the video of the sports game based on said tracking data, wherein each shot event represents a different stage of a shot, and the shot events correspond to one or more of a tennis ball being hit by a first player, the tennis ball passing a net, the tennis ball landing on a court, and the tennis ball being hit by a second player;

extracting video segments of the identified shot events from the video of the sports game;

generating shot event metadata for indexing the video segments;

computing a winning probability matrix comprising winning probabilities at point level by a winning probability model of the sports game, based on said shot event metadata;

computing a point excitement matrix based on said shot event metadata, wherein the point excitement matrix comprises one or more excitement weights pertaining to one or more of shot variety, final shot quality, rally length, overall shot quality, winners and errors, return improbability, or average unreturnability occurring within a rally; and

generating a sports game highlight video based on said winning probability matrix and point excitement matrix,

wherein the step of generating a sports game highlight video further includes:

ranking video segments according to deviations of actual outcomes of the sports game from the corresponding winning probabilities in said winning probability matrix,

concatenating the ranked video segments,

generating tracking model videos from the tracking data so that the tracking model video includes visual presentations of the tracking data, and

merging video segments with tracking model videos corresponding to the same shot.

2 . The method for generating a sports game highlight video according to claim 1 , wherein the step of computing the winning probability matrix comprises performing statistical analysis based on player historical statistics comprising performance statistics of the player.

3 . The method for generating a sports game highlight video according to claim 1 , wherein the step of computing the winning probability matrix comprises evaluating point state information of the sports game, wherein the point state information is obtained from a scoring feed or by analyzing the video of the sports game.

4 . The method for generating a sports game highlight video according to claim 1 , wherein the winning probability model comprises a point level probability model for evaluating the winning probabilities at point level.

5 . The method for generating a sports game highlight video according to claim 4 , wherein the winning probability model further comprises at least one of a game level probability model built upon said point level probability model, for evaluating the winning probabilities at game level, a set level probability model built upon said game level probability model, for evaluating the winning probabilities at set level, or a match level probability model built upon said set level probability model, for evaluating the winning probabilities at match level.

6 . The method for generating a sports game highlight video according to claim 1 , wherein the step of computing the winning probability matrix comprises using a machine learning algorithm trained by player historical statistics comprising performance statistics of the player.

7 . The method for generating a sports game highlight video according to claim 1 , wherein the step of generating a sports game highlight video further comprises:

generating tracking model videos from tracking data; and

merging video segments with tracking model videos corresponding to the same shot.

8 . The method for generating a sports game highlight video according to claim 1 , wherein the sports game is selected from the group consisting of tennis, badminton, table tennis, squash and volleyball.

9 . A computer program product comprising computer readable instructions which, when loaded onto a computer, configure the computer to perform a method according to claim 1 .

10 . An apparatus for generating a sports game highlight video, comprising circuitry configured to:

receive video of the sports game from at least one image capture device;

perform object tracking analysis on the video to generate tracking data providing ball trajectory and player position information;

identify a plurality of shot events in the video of the sports game based on said tracking data, wherein each shot event represents a different stage of a shot, and the shot events correspond to one or more of a tennis ball being hit by a first player, the tennis ball passing a net, the tennis ball landing on a court, and the tennis ball being hit by a second player;

extract video segments of the identified shot events from the video of the sports game;

generate shot event metadata for indexing the video segments;

compute a winning probability matrix comprising winning probabilities at point level by a winning probability model of the sports game, based on said shot event metadata;

compute a point excitement matrix based on said shot event metadata, wherein the point excitement matrix comprises one or more excitement weights pertaining to one or more of shot variety, final shot quality, rally length, overall shot quality, winners and errors, return improbability, or average unreturnability occurring within a rally; and

generate a sports game highlight video based on said winning probability matrix and point excitement matrix,

wherein the step of generating a sports game highlight video further includes:

ranking video segments according to deviations of actual outcomes of the sports game from the corresponding winning probabilities in said winning probability matrix,

concatenating the ranked video segments,

generating tracking model videos from the tracking data so that the tracking model video includes visual presentations of the tracking data, and

merging video segments with tracking model videos corresponding to the same shot.

11 . The apparatus for generating a sports game highlight video according to claim 10 , wherein the circuitry is further configured so that the step of computing the winning probability matrix comprises performing statistical analysis based on player historical statistics comprising performance statistics of the player.

12 . The apparatus for generating a sports game highlight video according to claim 10 , wherein the circuitry is further configured so that the step of computing the winning probability matrix comprises evaluating point state information of the sports game, wherein the point state information is obtained from a scoring feed or by analysing the video of the sports game.

13 . The apparatus for generating a sports game highlight video according to claim 10 , wherein the winning probability model comprises a point level probability model for evaluating the winning probabilities at point level.

14 . The apparatus for generating a sports game highlight video according to claim 13 , wherein the winning probability model further comprises a game level probability model built upon said point level probability model, for evaluating the winning probabilities at game level.

15 . The apparatus for generating a sports game highlight video according to claim 14 , wherein the winning probability model further comprises a set level probability model built upon said game level probability model, for evaluating the winning probabilities at set level.

16 . The apparatus for generating a sports game highlight video according to claim 15 , wherein the winning probability model further comprises a match level probability model built upon said set level probability model, for evaluating the winning probabilities at match level.

17 . The apparatus for generating a sports game highlight video according to claim 10 , wherein the circuitry is further configured so that the step of computing the winning probability matrix comprises using a machine learning algorithm trained by player historical statistics comprising performance statistics of the player.

Assignments (2)

Priority Claims (1)

Continuity (1)

References Cited (21)