INTERACTIVE FORMATION ANALYSIS IN SPORTS UTILIZING SEMI-SUPERVISED METHODS
A computing system identifies player tracking data and event data corresponding to a match. The match includes a first team and a second team. The player tracking data includes coordinate positions of each player during the event. The event data defines events that occur during the match. The computing system divides the player tracking data into a plurality of segments based on the event information. For each segment of the plurality of segments, the computing system learns a first formation associated with a respective team in possession. For each segment of the plurality of segments, the computing system learns a second formation associated with a respective team not in possession. The computing system maps each first formation to a first class of known formation clusters. The computing system maps each second formation to a second class of known formation clusters.
1 . A computer-implemented method for identifying a team formation, the computer-implemented method comprising:
receiving, by one or more processors, tracking data for at least one event, wherein the tracking data corresponds to at least one team, and wherein the at least one team includes one or more players;
segmenting, by the one or more processors, the tracking data into a plurality of segments associated with the at least one event;
determining, by the one or more processors, at least one formation for each of the plurality of segments for the at least one team;
mapping, by the one or more processors, the at least one formation to a formation cluster template based on the tracking data;
detecting, by the one or more processors, a formation change based on the mapping; and
outputting, by the one or more processors, a graphical output that corresponds to the formation change.
2 . The computer-implemented method of claim 1 , wherein the mapping includes mapping a player position for the one or more players to a role distribution in the formation cluster template.
3 . The computer-implemented method of claim 1 , the computer-implemented method further comprising:
normalizing, by the one or more processors, the tracking data of at least one of the plurality of segments.
4 . The computer-implemented method of claim 3 , the computer-implemented method further comprising:
determining, by the one or more processors, at least one average player position based on the normalized tracking data; and
initializing, by the one or more processors, the normalized tracking data based on the at least one average player position.
5 . The computer-implemented method of claim 4 , wherein the initializing the normalized tracking data includes:
assigning, by the one or more processors, the normalized at least one average player position as an initial role for the corresponding one or more players in the formation cluster template.
6 . The computer-implemented method of claim 1 , wherein the mapping the at least one formation to the formation cluster template based on the tracking data includes:
mapping, by the one or more processors, the at least one formation to a semantic label to detect the formation change.
7 . The computer-implemented method of claim 1 , wherein the at least one event includes at least one of: a red card event, an ejection event, a technical foul event, a flagrant foul event, a player disqualification event, a substitution event, a half event, a period event, a quarter event, and an overtime event.
8 . A computer system for identifying a team formation, the computer system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving, by the at least one processor, tracking data for at least one event, wherein the tracking data corresponds to at least one team, and wherein the at least one team includes one or more players;
segmenting, by the at least one processor, the tracking data into a plurality of segments associated with the at least one event;
determining, by the at least one processor, at least one formation for each of the plurality of segments for the at least one team;
mapping, by the at least one processor, the at least one formation to a formation cluster template based on the tracking data;
detecting, by the at least one processor, a formation change based on the mapping; and
outputting, by the at least one processor, a graphical output that corresponds to the formation change.
9 . The computer system of claim 8 , wherein the mapping includes mapping a player position for the one or more players to a role distribution in the formation cluster template.
10 . The computer system of claim 8 , the operations further comprising:
normalizing, by the at least one processor, the tracking data of at least one of the plurality of segments.
11 . The computer system of claim 10 , the operations further comprising:
determining, by the at least one processor, at least one average player position based on the normalized tracking data; and
initializing, by the at least one processor, the normalized tracking data based on the at least one average player position.
12 . The computer system of claim 11 , wherein the initializing the normalized tracking data includes:
assigning, by the at least one processor, the normalized at least one average player position as an initial role for the corresponding one or more players in the formation cluster template.
13 . The computer system of claim 8 , wherein the mapping the at least one formation to the formation cluster template based on the tracking data includes:
mapping, by the at least one processor, the at least one formation to a semantic label to detect the formation change.
14 . The computer system of claim 8 , wherein the at least one event includes at least one of: a red card event, an ejection event, a technical foul event, a flagrant foul event, a player disqualification event, a substitution event, a half event, a period event, a quarter event, and an overtime event.
15 . A non-transitory computer-readable medium containing instructions that, when executed by a processor, cause the processor to perform operations for identifying a team formation, the operations comprising:
receiving tracking data for at least one event, wherein the tracking data corresponds to at least one team, and wherein the at least one team includes one or more players;
segmenting the tracking data into a plurality of segments associated with the at least one event;
determining at least one formation for each of the plurality of segments for the at least one team;
mapping the at least one formation to a formation cluster template based on the tracking data;
detecting a formation change based on the mapping; and
outputting a graphical output that corresponds to the formation change.
16 . The non-transitory computer-readable medium of claim 15 , wherein the mapping includes mapping a player position for the one or more players to a role distribution in the formation cluster template.
17 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
normalizing the tracking data of at least one of the plurality of segments.
18 . The non-transitory computer-readable medium of claim 17 , the operations further comprising:
determining at least one average player position based on the normalized tracking data; and
initializing the normalized tracking data based on the at least one average player position.
19 . The non-transitory computer-readable medium of claim 18 , wherein the initializing the normalized tracking data includes:
assigning the normalized at least one average player position as an initial role for the corresponding one or more players in the formation cluster template.
20 . The non-transitory computer-readable medium of claim 15 , wherein the mapping the at least one formation to the formation cluster template based on the tracking data includes:
mapping the at least one formation to a semantic label to detect the formation change.