Investigating the Sketchplan: A Novel Way of Identifying Tactical Behavior in Massive Soccer Datasets

Daniel Seebacher, Thomas Polk, Halldor Janetzko, Daniel A. Keim, Tobias Schreck, Manuel Stein

Research output: Contribution to journalArticlepeer-review

Abstract

Coaches and analysts prepare for upcoming matches by identifying common patterns in the positioning and movement of the competing teams in specific situations. Existing approaches in this domain typically rely on manual video analysis and formation discussion using whiteboards; or expert systems that rely on state-of-the-art video and trajectory visualization techniques and advanced user interaction. We bridge the gap between these approaches by contributing a light-weight, simplified interaction and visualization system, which we conceptualized in an iterative design study with the coaching team of a European first league soccer team. Our approach is walk-up usable by all domain stakeholders, and at the same time, can leverage advanced data retrieval and analysis techniques: a virtual magnetic tactic-board. Users place and move digital magnets on a virtual tactic-board, and these interactions get translated to spatio-temporal queries, used to retrieve relevant situations from massive team movement data. Despite such seemingly imprecise query input, our approach is highly usable, supports quick user exploration, and retrieval of relevant results via query relaxation. Appropriate simplified result visualization supports in-depth analyses to explore team behavior, such as formation detection, movement analysis, and what-if analysis. We evaluated our approach with several experts from European first league soccer clubs. The results show that our approach makes the complex analytical processes needed for the identification of tactical behavior directly accessible to domain experts for the first time, demonstrating our support of coaches in preparation for future encounters.

Original languageEnglish
Pages (from-to)1-1
Number of pages1
JournalIEEE Transactions on Visualization and Computer Graphics
Early online date13 Dec 2021
DOIs
Publication statusE-pub ahead of print - 13 Dec 2021

Keywords

  • Data analysis
  • Data visualization
  • Europe
  • Magnetic domains
  • Soccer Analytics
  • Sport Analytics
  • Sports
  • Trajectory
  • Visual Analytics
  • Visualization

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fields of Expertise

  • Information, Communication & Computing

Fingerprint

Dive into the research topics of 'Investigating the Sketchplan: A Novel Way of Identifying Tactical Behavior in Massive Soccer Datasets'. Together they form a unique fingerprint.

Cite this