Visual Computing

University of Konstanz
2014 IEEE Conference on Visual Analytics Science and Technology (VAST)

Feature-driven visual analytics of soccer data

H. Janetzko, D. Sacha, M. Stein, T. Schreck, D. Keim, O. Deussen

Abstract

Soccer is one the most popular sports today and also very interesting from an scientific point of view. We present a system for analyzing high-frequency position-based soccer data at various levels of detail, allowing to interactively explore and analyze for movement features and game events. Our Visual Analytics method covers single-player, multi-player and event-based analytical views. Depending on the task the most promising features are semi-automatically selected, processed, and visualized. Our aim is to help soccer analysts in finding the most important and interesting events in a match. We present a flexible, modular, and expandable layer-based system allowing in-depth analysis. The integration of Visual Analytics techniques into the analysis process enables the analyst to find interesting events based on classification and allows, by a set of custom views, to communicate the found results. The feedback loop in the Visual Analytics pipeline helps to further improve the classification results. We evaluate our approach by investigating real-world soccer matches and collecting additional expert feedback. Several use cases and findings illustrate the capabilities of our approach.

BibTeX

@inproceedings{Janetzko2014Featuredrivenvisual,
  author     = {H. Janetzko and D. Sacha and M. Stein and T. Schreck and D. Keim and O. Deussen},
  booktitle  = {2014 IEEE Conference on Visual Analytics Science and Technology (VAST)},
  doi        = {10.1109/VAST.2014.7042477},
  keywords   = {data analysis;data visualisation;pattern classification;sport;classification results;data analysis;event-based analytical view;feature-driven visual analytics;feedback loop;game events;high-frequency position-based soccer data;movement features;multiplayer analytical view;single-player analytical view;soccer match;visual analytics method;Data mining;Data visualization;Feature extraction;Games;Trajectory;Visual analytics;Soccer Analysis;Sport Analytics;Visual Analytics},
  month      = {oct},
  pages      = {13-22},
  title      = {Feature-driven visual analytics of soccer data},
  year       = {2014},
}

Supplemental Material

Paper (.pdf, 10.8 MB)