SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data

Hyunsung Kim; Bit Kim; Dongwook Chung; Jinsung Yoon; Sang Ki Ko

doi:10.1145/3534678.3539150

SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data

Hyunsung Kim, Bit Kim, Dongwook Chung, Jinsung Yoon, Sang Ki Ko

Department of Artificial Intelligence

Fitogether Inc.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

In fluid team sports such as soccer and basketball, analyzing team formation is one of the most intuitive ways to understand tactics from domain participants' point of view. However, existing approaches either assume that team formation is consistent throughout a match or assign formations frame-by-frame, which disagree with real situations. To tackle this issue, we propose a change-point detection framework named SoccerCPD that distinguishes tactically intended formation and role changes from temporary changes in soccer matches. We first assign roles to players frame-by-frame and perform two-step change-point detections: (1) formation change-point detection based on the sequence of role-adjacency matrices and (2) role change-point detection based on the sequence of role permutations. The evaluation of SoccerCPD using the ground truth annotated by domain experts shows that our method accurately detects the points of tactical changes and estimates the formation and role assignment per segment. Lastly, we introduce practical use-cases that domain participants can easily interpret and utilize.

Original language	English
Title of host publication	KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery
Pages	3146-3156
Number of pages	11
ISBN (Electronic)	9781450393850
DOIs	https://doi.org/10.1145/3534678.3539150
State	Published - 14 Aug 2022
Event	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States Duration: 14 Aug 2022 → 18 Aug 2022

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/Territory	United States
City	Washington
Period	14/08/22 → 18/08/22

Keywords

change-point detection
formation analysis
gps tracking data
spatiotemporal data analysis
sports analytics

Access to Document

10.1145/3534678.3539150

Cite this

Kim, H., Kim, B., Chung, D., Yoon, J., & Ko, S. K. (2022). SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data. In KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 3146-3156). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery. https://doi.org/10.1145/3534678.3539150

Kim, Hyunsung ; Kim, Bit ; Chung, Dongwook et al. / SoccerCPD : Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data. KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2022. pp. 3146-3156 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{54d530dd219e41ea8b90ed59ea6ab717,

title = "SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data",

abstract = "In fluid team sports such as soccer and basketball, analyzing team formation is one of the most intuitive ways to understand tactics from domain participants' point of view. However, existing approaches either assume that team formation is consistent throughout a match or assign formations frame-by-frame, which disagree with real situations. To tackle this issue, we propose a change-point detection framework named SoccerCPD that distinguishes tactically intended formation and role changes from temporary changes in soccer matches. We first assign roles to players frame-by-frame and perform two-step change-point detections: (1) formation change-point detection based on the sequence of role-adjacency matrices and (2) role change-point detection based on the sequence of role permutations. The evaluation of SoccerCPD using the ground truth annotated by domain experts shows that our method accurately detects the points of tactical changes and estimates the formation and role assignment per segment. Lastly, we introduce practical use-cases that domain participants can easily interpret and utilize.",

keywords = "change-point detection, formation analysis, gps tracking data, spatiotemporal data analysis, sports analytics",

author = "Hyunsung Kim and Bit Kim and Dongwook Chung and Jinsung Yoon and Ko, {Sang Ki}",

note = "Publisher Copyright: {\textcopyright} 2022 Owner/Author.; 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; Conference date: 14-08-2022 Through 18-08-2022",

year = "2022",

month = aug,

day = "14",

doi = "10.1145/3534678.3539150",

language = "English",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery",

pages = "3146--3156",

booktitle = "KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

}

Kim, H, Kim, B, Chung, D, Yoon, J & Ko, SK 2022, SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data. in KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, pp. 3146-3156, 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022, Washington, United States, 14/08/22. https://doi.org/10.1145/3534678.3539150

SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data. / Kim, Hyunsung; Kim, Bit; Chung, Dongwook et al.
KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2022. p. 3146-3156 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SoccerCPD

T2 - 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022

AU - Kim, Hyunsung

AU - Kim, Bit

AU - Chung, Dongwook

AU - Yoon, Jinsung

AU - Ko, Sang Ki

PY - 2022/8/14

Y1 - 2022/8/14

N2 - In fluid team sports such as soccer and basketball, analyzing team formation is one of the most intuitive ways to understand tactics from domain participants' point of view. However, existing approaches either assume that team formation is consistent throughout a match or assign formations frame-by-frame, which disagree with real situations. To tackle this issue, we propose a change-point detection framework named SoccerCPD that distinguishes tactically intended formation and role changes from temporary changes in soccer matches. We first assign roles to players frame-by-frame and perform two-step change-point detections: (1) formation change-point detection based on the sequence of role-adjacency matrices and (2) role change-point detection based on the sequence of role permutations. The evaluation of SoccerCPD using the ground truth annotated by domain experts shows that our method accurately detects the points of tactical changes and estimates the formation and role assignment per segment. Lastly, we introduce practical use-cases that domain participants can easily interpret and utilize.

AB - In fluid team sports such as soccer and basketball, analyzing team formation is one of the most intuitive ways to understand tactics from domain participants' point of view. However, existing approaches either assume that team formation is consistent throughout a match or assign formations frame-by-frame, which disagree with real situations. To tackle this issue, we propose a change-point detection framework named SoccerCPD that distinguishes tactically intended formation and role changes from temporary changes in soccer matches. We first assign roles to players frame-by-frame and perform two-step change-point detections: (1) formation change-point detection based on the sequence of role-adjacency matrices and (2) role change-point detection based on the sequence of role permutations. The evaluation of SoccerCPD using the ground truth annotated by domain experts shows that our method accurately detects the points of tactical changes and estimates the formation and role assignment per segment. Lastly, we introduce practical use-cases that domain participants can easily interpret and utilize.

KW - change-point detection

KW - formation analysis

KW - gps tracking data

KW - spatiotemporal data analysis

KW - sports analytics

UR - http://www.scopus.com/inward/record.url?scp=85137142992&partnerID=8YFLogxK

U2 - 10.1145/3534678.3539150

DO - 10.1145/3534678.3539150

M3 - Conference contribution

AN - SCOPUS:85137142992

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 3146

EP - 3156

BT - KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

Y2 - 14 August 2022 through 18 August 2022

ER -

Kim H, Kim B, Chung D, Yoon J, Ko SK. SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data. In KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2022. p. 3146-3156. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3534678.3539150

SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this