Visual soccer match analysis using spatiotemporal positions of players

Abstract Soccer is a fascinating sport that captures the attention of millions of people in the world. Professional soccer teams, as well as the broadcasting media, have a deep interest in the analysis of soccer matches. Statistical summaries are the most widely used approach to describe a soccer match. However, they often fail to capture the evolution and changes of strategies that happen during a game. In this work, we present visual designs to help understanding a soccer match from the spatiotemporal position of players. We receive as input the coordinates of each player throughout the match, as well as the associated events. We present a pixel-oriented layout that summarizes the changes of player positions and tactical schemes during the match. Also, we revisit a technique used for flow analysis to help us identify where does a player move from a given region in the field. We developed our approach in conjunction with colleagues from physical education with experience in soccer analysis, as well as experts on soccer data extraction. We demonstrate the utility of our approach in several match situations, and provide the feedback given by the experts.

[1]  Christopher J. Anderson,et al.  The numbers game: why everything you know about football is wrong , 2014 .

[2]  Sridha Sridharan,et al.  Large-Scale Analysis of Formations in Soccer , 2013, 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[3]  Fabian Beck,et al.  Visualizing the Evolution of Communities in Dynamic Graphs , 2015, Comput. Graph. Forum.

[4]  Jean-Daniel Fekete,et al.  MatLink: Enhanced Matrix Visualization for Analyzing Social Networks , 2007, INTERACT.

[5]  Daniel A. Keim,et al.  Visual Analysis of Time‐Series Similarities for Anomaly Detection in Sensor Networks , 2014, Comput. Graph. Forum.

[6]  Gennady L. Andrienko,et al.  Spatio-temporal aggregation for visual analysis of movements , 2008, 2008 IEEE Symposium on Visual Analytics Science and Technology.

[7]  Kazuo Misue Visualization of Team Skills in Project-Based Learning , 2013, CloudCom 2013.

[8]  Ki-Joune Li,et al.  Spatial and spatiotemporal analysis of soccer , 2011, GIS.

[9]  Carlos Lago-Peñas,et al.  Game-Related Statistics that Discriminated Winning, Drawing and Losing Teams from the Spanish Soccer League. , 2010, Journal of sports science & medicine.

[10]  Daniel A. Keim,et al.  Feature-driven visual analytics of soccer data , 2014, 2014 IEEE Conference on Visual Analytics Science and Technology (VAST).

[11]  Keith Davids,et al.  Capturing complex, non-linear team behaviours during competitive football performance , 2013, Journal of Systems Science and Complexity.

[12]  Sridha Sridharan,et al.  Large-Scale Analysis of Soccer Matches Using Spatiotemporal Tracking Data , 2014, 2014 IEEE International Conference on Data Mining.

[13]  Nathalie Henry Riche,et al.  Dual Adjacency Matrix: Exploring Link Groups in Dense Networks , 2015, Comput. Graph. Forum.

[14]  Louise Barrett,et al.  Space Transformation for Understanding Group Movement , 2013, IEEE Transactions on Visualization and Computer Graphics.

[15]  Tobias Schreck,et al.  Visual-Interactive Search for Soccer Trajectories to Identify Interesting Game Situations , 2016, Visualization and Data Analysis.

[16]  Halldór Janetzko,et al.  Enhancing Parallel Coordinates: Statistical Visualizations for Analyzing Soccer Data , 2016, Visualization and Data Analysis.

[17]  Min Chen,et al.  Knowledge-Assisted Ranking: A Visual Analytic Application for Sports Event Data , 2016, IEEE Computer Graphics and Applications.

[18]  Bruno Travassos,et al.  Spatial dynamics of team sports exposed by Voronoi diagrams. , 2012, Human movement science.

[19]  Andrew Vande Moere,et al.  Towards Classifying Visualization in Team Sports , 2006, International Conference on Computer Graphics, Imaging and Visualisation (CGIV'06).

[20]  Daniel A. Keim,et al.  Designing Pixel-Oriented Visualization Techniques: Theory and Applications , 2000, IEEE Trans. Vis. Comput. Graph..

[21]  Cláudio T. Silva,et al.  Visualizing Running Races through the Multivariate Time-Series of Multiple Runners , 2013, 2013 XXVI Conference on Graphics, Patterns and Images.

[22]  Min Chen,et al.  MatchPad: Interactive Glyph‐Based Visualization for Real‐Time Sports Performance Analysis , 2012, Comput. Graph. Forum.

[23]  Joachim Gudmundsson,et al.  Spatio-Temporal Analysis of Team Sports , 2016, ACM Comput. Surv..

[24]  Charles Perin,et al.  A table!: improving temporal navigation in soccer ranking tables , 2014, CHI.

[25]  V. Di Salvo,et al.  Performance Characteristics According to Playing Position in Elite Soccer , 2006, International journal of sports medicine.

[26]  Daniel Weiskopf,et al.  Pathline glyphs , 2014, Comput. Graph. Forum.

[27]  Qing Wang,et al.  Discerning Tactical Patterns for Professional Soccer Teams: An Enhanced Topic Model with Applications , 2015, KDD.

[28]  Peter Carr,et al.  Assessing team strategy using spatiotemporal data , 2013, KDD.

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