Modeling and Recognising Team Strategies, Tactics and Tendencies in Sports

Project Members

Patrick Lucey (Disney Research Pittsburgh)
Alina Bialkowski (Queensland University of Technology)
Peter Carr (Disney Research Pittsburgh)
Yaser Sheikh (Disney Research Pittsburgh/Carnegie Mellon University)
Iain Matthews (Disney Research Pittsburgh)

 

Project_ModelingTeamTendencies_teaser

We introduce a method to represent and discover adversarial group behavior in a continuous domain. In comparison to other types of behavior, adversarial behavior is heavily structured as the location of an player (or agent) is dependent both on their teammates and adversaries, in addition to the tactics or strategies of the team. Our method can exploit this relationship through the use of a spatiotemporal basis model. As players constantly change roles during a match, we show that employing a “role-based” representation instead of one based on player identity can best exploit the playing structure. As vision-based systems currently do not provide perfect detection/tracking (e.g. missed or false detections), we show that our approach can “denoise” the signal and assign player roles which enables analysis of team formation and plays in continuous sports occur. Finding a compact representation allows significant temporal analysis to occur, which was previously prohibitive due to the dimensionality of the signal.

Publications

Chalkboarding- A New Spatiotemporal Query Paradigm for Sports Play Retrieval-Thumbnail

Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval
March 7, 2016
Intelligent User Interfaces (IUI) 2016
Paper File [pdf, 11.85 MB]

Quality vs Quantity”- Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data-Thumbnail

“Quality vs Quantity”: Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data
February 27, 2015
MIT Sloan Sports Analytics Conference 2015
Paper File [pdf, 2.39 MB]

Large-Scale Analysis of Soccer Matches using-Thumbnail

Large-Scale Analysis of Soccer Matches using Spatiotemporal Tracking Data
December 14, 2014
International Conference on Data Mining (ICDM) 2014
Paper File [pdf, 3.66 MB]

Identifying Team Style in Soccer using Formations from Spatiotemporal Tracking Data-Thumbnail

Identifying Team Style in Soccer using Formations from Spatiotemporal Tracking Data
December 13, 2014
International Workshop on Spatial and Spatiotemporal Data Mining 2014
Paper File [pdf, 6.89 MB]

Representing Team Behaviours from Noisy Data using Player Role-Thumbnail

Representing Team Behaviours from Noisy Data using Player Role
December 10, 2014
Computer Vision in Sports 2014
Paper File [pdf, 1.85 MB]

How to Get an Open Shot-Analyzing Team Movement in Basketball using Tracking Data-thumbnail

“How to Get an Open Shot”: Analyzing Team Movement in Basketball using Tracking Data
April 30, 2014
MIT Sloan Sports Analytics Conference 2014
Paper File [pdf, 2.88 MB]

“How to Get an Open Shot”- Analyzing Team Movement in Basketball using Tracking Data-Thumbnail

“How to Get an Open Shot”: Analyzing Team Movement in Basketball using Tracking Data
April 30, 2014
MIT Sloan Sports Analytics Conference 2014
Paper File [pdf, 2.88 MB]

Large-Scale Analysis of Formations in Soccer-thumbnail

Large-Scale Analysis of Formations in Soccer
November 26, 2013
The International Conference on Digital Image Computing: Techniques and Applications (DICTA) 2013
Paper File [pdf, 5.74 MB]

Recognizing Team Activities from Noisy Data-Thumbnail

Recognizing Team Activities from Noisy Data
June 28, 2013
IEEE International Workshop on Computer Vision in Sports (CVSports) 2013
Paper File [pdf, 1.85 MB]

Representing and Discovering Adversarial Team Behaviors Using Player Roles-thumbnail

Representing and Discovering Adversarial Team Behaviors Using Player Roles
June 25, 2013
IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2013
Paper File [pdf, 7.17 MB]

Copyright Notice

The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.