Discovering Team Structures in Soccer from Spatiotemporal Data
In team sports like soccer, utilizing tracking data for analysis is challenging due to the dynamic and multi-agent nature of the data. The biggest issue surrounds the changing of positions or "roles" between players on a frame-to-frame basis, which causes misalignment of the data and makes...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on knowledge and data engineering 2016-10, Vol.28 (10), p.2596-2605 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2605 |
|---|---|
| container_issue | 10 |
| container_start_page | 2596 |
| container_title | IEEE transactions on knowledge and data engineering |
| container_volume | 28 |
| creator | Bialkowski, Alina Lucey, Patrick Carr, Peter Matthews, Iain Sridharan, Sridha Fookes, Clinton |
| description | In team sports like soccer, utilizing tracking data for analysis is challenging due to the dynamic and multi-agent nature of the data. The biggest issue surrounds the changing of positions or "roles" between players on a frame-to-frame basis, which causes misalignment of the data and makes it difficult to perform team analysis. In this paper, we present an unsupervised method to learn a formation template which allows us to "align" the tracking data at the frame level. Not only does this approach give important contextual information to facilitate large-scale analysis (e.g., we know when a player is in the left-wing position compared to left-back), it also yields the team structure or "formation" which serves as a strong descriptor for identifying a team's style. The utility of the approach is demonstrated on a full season of player and ball tracking data from a professional soccer league consisting of over 21.5 million frames of player tracking data. |
| doi_str_mv | 10.1109/TKDE.2016.2581158 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_1830949501</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7492601</ieee_id><sourcerecordid>4223618001</sourcerecordid><originalsourceid>FETCH-LOGICAL-c402t-8a7eae735beb1f6c65f2486f23564a506f0a15dc06cef7b27ab8542dfc2a0eae3</originalsourceid><addsrcrecordid>eNo9kE1LAzEQhoMoWKs_QLwseN46k02y2Ysgbf3AgofWc8imE9nSNmuyK_jv3dLiaQbmed-Bh7FbhAkiVA-r99l8wgHVhEuNKPUZG6GUOudY4fmwg8BcFKK8ZFcpbQBAlxpH7HHWJBd-KDb7r2xFdpctu9i7ro-UsmafLYNzFDMfw3BpbdeEjnZtiHabzWxnr9mFt9tEN6c5Zp_P89X0NV98vLxNnxa5E8C7XNuSLJWFrKlGr5ySngutPC-kElaC8mBRrh0oR76seWlrLQVfe8ctDMlizO6PvW0M3z2lzmxCH_fDS4O6gEpUEnCg8Ei5GFKK5E0bm52NvwbBHDSZgyZz0GROmobM3THTENE_X4qKq6HxDxmhY6M</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1830949501</pqid></control><display><type>article</type><title>Discovering Team Structures in Soccer from Spatiotemporal Data</title><source>IEEE Electronic Library (IEL)</source><creator>Bialkowski, Alina ; Lucey, Patrick ; Carr, Peter ; Matthews, Iain ; Sridharan, Sridha ; Fookes, Clinton</creator><creatorcontrib>Bialkowski, Alina ; Lucey, Patrick ; Carr, Peter ; Matthews, Iain ; Sridharan, Sridha ; Fookes, Clinton</creatorcontrib><description>In team sports like soccer, utilizing tracking data for analysis is challenging due to the dynamic and multi-agent nature of the data. The biggest issue surrounds the changing of positions or "roles" between players on a frame-to-frame basis, which causes misalignment of the data and makes it difficult to perform team analysis. In this paper, we present an unsupervised method to learn a formation template which allows us to "align" the tracking data at the frame level. Not only does this approach give important contextual information to facilitate large-scale analysis (e.g., we know when a player is in the left-wing position compared to left-back), it also yields the team structure or "formation" which serves as a strong descriptor for identifying a team's style. The utility of the approach is demonstrated on a full season of player and ball tracking data from a professional soccer league consisting of over 21.5 million frames of player tracking data.</description><identifier>ISSN: 1041-4347</identifier><identifier>EISSN: 1558-2191</identifier><identifier>DOI: 10.1109/TKDE.2016.2581158</identifier><identifier>CODEN: ITKEEH</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>alignment ; Distribution functions ; Entropy ; Formation ; Graphical models ; group behaviour ; Heating ; multi-agent ; Probability density function ; role ; Satellites ; soccer ; spatio-temporal data ; Spatiotemporal phenomena ; sports analytics ; team analysis ; Trajectory</subject><ispartof>IEEE transactions on knowledge and data engineering, 2016-10, Vol.28 (10), p.2596-2605</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2016</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c402t-8a7eae735beb1f6c65f2486f23564a506f0a15dc06cef7b27ab8542dfc2a0eae3</citedby><cites>FETCH-LOGICAL-c402t-8a7eae735beb1f6c65f2486f23564a506f0a15dc06cef7b27ab8542dfc2a0eae3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7492601$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7492601$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Bialkowski, Alina</creatorcontrib><creatorcontrib>Lucey, Patrick</creatorcontrib><creatorcontrib>Carr, Peter</creatorcontrib><creatorcontrib>Matthews, Iain</creatorcontrib><creatorcontrib>Sridharan, Sridha</creatorcontrib><creatorcontrib>Fookes, Clinton</creatorcontrib><title>Discovering Team Structures in Soccer from Spatiotemporal Data</title><title>IEEE transactions on knowledge and data engineering</title><addtitle>TKDE</addtitle><description>In team sports like soccer, utilizing tracking data for analysis is challenging due to the dynamic and multi-agent nature of the data. The biggest issue surrounds the changing of positions or "roles" between players on a frame-to-frame basis, which causes misalignment of the data and makes it difficult to perform team analysis. In this paper, we present an unsupervised method to learn a formation template which allows us to "align" the tracking data at the frame level. Not only does this approach give important contextual information to facilitate large-scale analysis (e.g., we know when a player is in the left-wing position compared to left-back), it also yields the team structure or "formation" which serves as a strong descriptor for identifying a team's style. The utility of the approach is demonstrated on a full season of player and ball tracking data from a professional soccer league consisting of over 21.5 million frames of player tracking data.</description><subject>alignment</subject><subject>Distribution functions</subject><subject>Entropy</subject><subject>Formation</subject><subject>Graphical models</subject><subject>group behaviour</subject><subject>Heating</subject><subject>multi-agent</subject><subject>Probability density function</subject><subject>role</subject><subject>Satellites</subject><subject>soccer</subject><subject>spatio-temporal data</subject><subject>Spatiotemporal phenomena</subject><subject>sports analytics</subject><subject>team analysis</subject><subject>Trajectory</subject><issn>1041-4347</issn><issn>1558-2191</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE1LAzEQhoMoWKs_QLwseN46k02y2Ysgbf3AgofWc8imE9nSNmuyK_jv3dLiaQbmed-Bh7FbhAkiVA-r99l8wgHVhEuNKPUZG6GUOudY4fmwg8BcFKK8ZFcpbQBAlxpH7HHWJBd-KDb7r2xFdpctu9i7ro-UsmafLYNzFDMfw3BpbdeEjnZtiHabzWxnr9mFt9tEN6c5Zp_P89X0NV98vLxNnxa5E8C7XNuSLJWFrKlGr5ySngutPC-kElaC8mBRrh0oR76seWlrLQVfe8ctDMlizO6PvW0M3z2lzmxCH_fDS4O6gEpUEnCg8Ei5GFKK5E0bm52NvwbBHDSZgyZz0GROmobM3THTENE_X4qKq6HxDxmhY6M</recordid><startdate>20161001</startdate><enddate>20161001</enddate><creator>Bialkowski, Alina</creator><creator>Lucey, Patrick</creator><creator>Carr, Peter</creator><creator>Matthews, Iain</creator><creator>Sridharan, Sridha</creator><creator>Fookes, Clinton</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20161001</creationdate><title>Discovering Team Structures in Soccer from Spatiotemporal Data</title><author>Bialkowski, Alina ; Lucey, Patrick ; Carr, Peter ; Matthews, Iain ; Sridharan, Sridha ; Fookes, Clinton</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c402t-8a7eae735beb1f6c65f2486f23564a506f0a15dc06cef7b27ab8542dfc2a0eae3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>alignment</topic><topic>Distribution functions</topic><topic>Entropy</topic><topic>Formation</topic><topic>Graphical models</topic><topic>group behaviour</topic><topic>Heating</topic><topic>multi-agent</topic><topic>Probability density function</topic><topic>role</topic><topic>Satellites</topic><topic>soccer</topic><topic>spatio-temporal data</topic><topic>Spatiotemporal phenomena</topic><topic>sports analytics</topic><topic>team analysis</topic><topic>Trajectory</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bialkowski, Alina</creatorcontrib><creatorcontrib>Lucey, Patrick</creatorcontrib><creatorcontrib>Carr, Peter</creatorcontrib><creatorcontrib>Matthews, Iain</creatorcontrib><creatorcontrib>Sridharan, Sridha</creatorcontrib><creatorcontrib>Fookes, Clinton</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on knowledge and data engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bialkowski, Alina</au><au>Lucey, Patrick</au><au>Carr, Peter</au><au>Matthews, Iain</au><au>Sridharan, Sridha</au><au>Fookes, Clinton</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Discovering Team Structures in Soccer from Spatiotemporal Data</atitle><jtitle>IEEE transactions on knowledge and data engineering</jtitle><stitle>TKDE</stitle><date>2016-10-01</date><risdate>2016</risdate><volume>28</volume><issue>10</issue><spage>2596</spage><epage>2605</epage><pages>2596-2605</pages><issn>1041-4347</issn><eissn>1558-2191</eissn><coden>ITKEEH</coden><abstract>In team sports like soccer, utilizing tracking data for analysis is challenging due to the dynamic and multi-agent nature of the data. The biggest issue surrounds the changing of positions or "roles" between players on a frame-to-frame basis, which causes misalignment of the data and makes it difficult to perform team analysis. In this paper, we present an unsupervised method to learn a formation template which allows us to "align" the tracking data at the frame level. Not only does this approach give important contextual information to facilitate large-scale analysis (e.g., we know when a player is in the left-wing position compared to left-back), it also yields the team structure or "formation" which serves as a strong descriptor for identifying a team's style. The utility of the approach is demonstrated on a full season of player and ball tracking data from a professional soccer league consisting of over 21.5 million frames of player tracking data.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TKDE.2016.2581158</doi><tpages>10</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1041-4347 |
| ispartof | IEEE transactions on knowledge and data engineering, 2016-10, Vol.28 (10), p.2596-2605 |
| issn | 1041-4347 1558-2191 |
| language | eng |
| recordid | cdi_proquest_journals_1830949501 |
| source | IEEE Electronic Library (IEL) |
| subjects | alignment Distribution functions Entropy Formation Graphical models group behaviour Heating multi-agent Probability density function role Satellites soccer spatio-temporal data Spatiotemporal phenomena sports analytics team analysis Trajectory |
| title | Discovering Team Structures in Soccer from Spatiotemporal Data |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T20%3A16%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Discovering%20Team%20Structures%20in%20Soccer%20from%20Spatiotemporal%20Data&rft.jtitle=IEEE%20transactions%20on%20knowledge%20and%20data%20engineering&rft.au=Bialkowski,%20Alina&rft.date=2016-10-01&rft.volume=28&rft.issue=10&rft.spage=2596&rft.epage=2605&rft.pages=2596-2605&rft.issn=1041-4347&rft.eissn=1558-2191&rft.coden=ITKEEH&rft_id=info:doi/10.1109/TKDE.2016.2581158&rft_dat=%3Cproquest_RIE%3E4223618001%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1830949501&rft_id=info:pmid/&rft_ieee_id=7492601&rfr_iscdi=true |