Analysing Team Formations in Football with the Static Qualitative Trajectory Calculus

In this paper, we introduce the Static Qualitative Trajectory Calculus (QTCS), a qualitative spatiotemporal method based on the Qualitative Trajectory Calculus (QTC), for team formation analysis in football. While methods for team formation analysis are mostly quantitative, QTCS enables the comparison of team formations by describing the relative positions between players in a qualitative manner, which is much more related to the way players position themselves on the field. To illustrate the method, we present a series of examples based on real football matches of a 2016-2017 European football competition. With QTCS, team formations of both an entire team as well as a smaller group of players can be described. Analysis of these formations can be done for multiple matches, thereby defining the playing style of a team, or at critical moments during a game, such as set pieces.

[1]  Murray R. Barrick,et al.  Relating member ability and personality to work-team processes and team effectiveness. , 1998 .

[2]  Hugo Sarmento,et al.  The Coaching Process in Football - A qualitative perspective , 2014 .

[3]  Wouter Frencken,et al.  Tactical Performance Analysis in Invasion Games , 2013 .

[4]  Udo Feuerhake,et al.  Recognition of Repetitive Movement Patterns - The Case of Football Analysis , 2016, ISPRS Int. J. Geo Inf..

[5]  Yisong Yue,et al.  “ How to Get an Open Shot ” : Analyzing Team Movement in Basketball using Tracking Data , 2014 .

[6]  Guy De Tré,et al.  The Double-Cross and the Generalization Concept as a Basis for Representing and Comparing Shapes of Polylines , 2005, OTM Workshops.

[7]  Kalyanmoy Deb,et al.  Multi-objective optimization and decision making approaches to cricket team selection , 2013, Appl. Soft Comput..

[8]  Frank Witlox,et al.  Representing moving objects in computer-based expert systems: the overtake event example , 2005, Expert Syst. Appl..

[9]  Yisong Yue,et al.  “Win at Home and Draw Away”: Automatic Formation Analysis Highlighting the Differences in Home and Away Team Behaviors , 2014 .

[10]  Tiziana D'Orazio,et al.  A review of vision-based systems for soccer video analysis , 2010, Pattern Recognit..

[11]  Nico Van de Weghe,et al.  QTC3D: Extending the Qualitative Trajectory Calculus to Three Dimensions , 2015, Inf. Sci..

[12]  Jürgen Perl,et al.  Tactical pattern recognition in soccer games by means of special self-organizing maps. , 2012, Human movement science.

[13]  Peter Stone,et al.  The UT Austin Villa 2003 Champion Simulator Coach: A Machine Learning Approach , 2004, RoboCup.

[14]  Daniel Memmert,et al.  Big data and tactical analysis in elite soccer: future challenges and opportunities for sports science , 2016, SpringerPlus.

[15]  Manuela M. Veloso,et al.  Learning the Sequential Coordinated Behavior of Teams from Observations , 2002, RoboCup.

[16]  Gerard Sierksma,et al.  Team formation: Matching quality supply and quality demand , 2003, Eur. J. Oper. Res..

[17]  Charles Perin,et al.  SoccerStories: A Kick-off for Visual Soccer Analysis , 2013, IEEE Transactions on Visualization and Computer Graphics.

[18]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[19]  Indriyati Atmosukarto,et al.  Automatic Recognition of Offensive Team Formation in American Football Plays , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[20]  Wolfgang I Schöllhorn,et al.  Identifying individuality and variability in team tactics by means of statistical shape analysis and multilayer perceptrons. , 2012, Human movement science.

[21]  J. Sampaio,et al.  Measuring Tactical Behaviour in Football , 2012, International Journal of Sports Medicine.

[22]  C. Carling.  Influence of opposition team formation on physical and skill-related performance in a professional soccer team , 2011 .

[23]  T. Barkowsky,et al.  The qualitative trajectory calculus on networks , 2007 .

[24]  Jaime Sampaio,et al.  Effect of player position on movement behaviour, physical and physiological performances during an 11-a-side football game , 2014, Journal of sports sciences.

[25]  Yaser Sheikh,et al.  Representing and Discovering Adversarial Team Behaviors Using Player Roles , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Huberto Ayanegui-Santiago.  Recognizing Team Formations in Multiagent Systems: Applications in Robotic Soccer , 2009, ICCCI.

[27]  Ubbo Visser,et al.  Recognizing Formations in Opponent Teams , 2000, RoboCup.

[28]  Nico Van de Weghe,et al.  Conceptual Neighbourhood Diagrams for Representing Moving Objects , 2005, ER.

[29]  B Dezman,et al.  Expert model of decision-making system for efficient orientation of basketball players to positions and roles in the game--empirical verification. , 2001, Collegium antropologicum.

[30]  Michael J Duncan,et al.  Match play demands of 11 versus 11 professional football using Global Positioning System tracking: Variations across common playing formations. , 2016, Human movement science.

[31]  Wouter Frencken,et al.  Variability of inter-team distances associated with match events in elite-standard soccer , 2012, Journal of sports sciences.