A Topic Model Approach to Representing and Classifying Football Plays

Handle URI:
http://hdl.handle.net/10754/556164
Title:
A Topic Model Approach to Representing and Classifying Football Plays
Authors:
Varadarajan, Jagannadan; Atmosukarto, Indriyati; Ahuja, Shaunak; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Ahuja, Narendra
Abstract:
We address the problem of modeling and classifying American Football offense teams’ plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more ef- ficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. To this end, we develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximiza- tion of both likelihood and inter-class margins of MedLDA in learning the topics allows us to learn semantically meaningful play type templates, as well as, classify different play types with 70% average accuracy. Furthermore, this method is extended to analyze individual player roles in classifying each play type. We validate our method on a large dataset comprising 271 play clips from real-world football games, which will be made publicly available for future comparisons.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
BMVA Press
Journal:
Proceedings of the British Machine Vision Conference
Conference/Event name:
2013 24th British Machine Vision Conference, BMVC 2013
Issue Date:
9-Sep-2013
DOI:
10.5244/C.27.64
Type:
Conference Paper
Additional Links:
http://www.bmva.org/bmvc/2013/Papers/paper0064/index.html; http://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/plays_topics_BMVC2013.pdf
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorVaradarajan, Jagannadanen
dc.contributor.authorAtmosukarto, Indriyatien
dc.contributor.authorAhuja, Shaunaken
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorAhuja, Narendraen
dc.date.accessioned2015-06-02T14:06:45Zen
dc.date.available2015-06-02T14:06:45Zen
dc.date.issued2013-09-09en
dc.identifier.doi10.5244/C.27.64en
dc.identifier.urihttp://hdl.handle.net/10754/556164en
dc.description.abstractWe address the problem of modeling and classifying American Football offense teams’ plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more ef- ficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. To this end, we develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximiza- tion of both likelihood and inter-class margins of MedLDA in learning the topics allows us to learn semantically meaningful play type templates, as well as, classify different play types with 70% average accuracy. Furthermore, this method is extended to analyze individual player roles in classifying each play type. We validate our method on a large dataset comprising 271 play clips from real-world football games, which will be made publicly available for future comparisons.en
dc.publisherBMVA Pressen
dc.relation.urlhttp://www.bmva.org/bmvc/2013/Papers/paper0064/index.htmlen
dc.relation.urlhttp://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/plays_topics_BMVC2013.pdfen
dc.rightsArchived with thanks to Proceedings of the British Machine Vision Conferenceen
dc.titleA Topic Model Approach to Representing and Classifying Football Playsen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalProceedings of the British Machine Vision Conferenceen
dc.conference.date9 September 2013 through 13 September 2013en
dc.conference.name2013 24th British Machine Vision Conference, BMVC 2013en
dc.conference.locationBristolen
dc.eprint.versionPost-printen
dc.contributor.institutionAdvanced Digital Sciences Center of Illinois, Singaporeen
dc.contributor.institutionDepartment of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign, 205 N. MatthewAvenue, Urbana, IL 61801, USAen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.