Visual Soccer Analytics: Understanding the Characteristics of Collective Team Movement Based on Feature-Driven Analysis and Abstraction

Abstract

With recent advances in sensor technologies, large amounts of movement data have become available in many application areas. A novel, promising application is the data-driven analysis of team sport. Specifically, soccer matches comprise rich, multivariate movement data at high temporal and geospatial resolution. Capturing and analyzing complex movement patterns and interdependencies between the players with respect to various characteristics is challenging. So far, soccer experts manually post-analyze game situations and depict certain patterns with respect to their experience. We propose a visual analysis system for interactive identification of soccer patterns and situations being of interest to the analyst. Our approach builds on a preliminary system, which is enhanced by semantic features defined together with a soccer domain expert. The system includes a range of useful visualizations to show the ranking of features over time and plots the change of game play situations, both helping the analyst to interpret complex game situations. A novel workflow includes improving the analysis process by a learning stage, taking into account user feedback. We evaluate our approach by analyzing real-world soccer matches, illustrate ISPRS Int. J. Geo-Inf. 2015, 4 2160 several use cases and collect additional expert feedback. The resulting findings are discussed with subject matter experts.

How to Make Sense of Team Sport Data: From Acquisition to Data Modeling and Research Aspects

“…We give an example of a set of potentially relevant events for soccer analysis in Figure 3. This list of events derived from our previous works on a continuously expanded system for feature-and event-based soccer analysis [21][22][23]. Although arguably it may be extensible, and is not tailored towards a specific model from Sport Science, we believe it is a practical starting point for reasoning about the types of events potentially useful for analysis.…”

“…The dangerousness for each region is mapped to the blue hue. White meaning safe, dark blue meaning dangerousnes; (c) Temporal visualization [22] displaying the occurence of user-selected events, like fouls, goals or exchanges; (d) Horizon graph [21] showing the feature speed for two defense players within a set time interval.…”

“…This data mining method can, for example, be used-to stay with the American Football example-to automatically identify in which passing pattern a new pass can be classified. We successfully used classification in one of our previous works [22] to detect dangerous situations. A dangerous situation in our case was a shot on the goal of a team.…”

A Review of Guidance Approaches in Visual Data Analysis: A Multifocal Perspective

“…Other aspects of this approach relate to the feedforward concept, thus we will discuss it in the next paragraph. Stein et al [SHJ∗15, SSS∗14a] propose a visual analytics approach supporting the analysis of soccer matches. By extracting the most interesting features from the data, the system is able to propose to the user interesting events that characterize the match.…”

Bring It to the Pitch: Combining Video and Movement Data to Enhance Team Sport Analysis

“…The sorting is aimed for the efficient classification of match recordings for subsequent analysis and evaluation of the team performance. An approach for the interactive determination and analysis of interesting events during a soccer match is proposed by Janetzko et al [44] and extended with an application-specific visualization by Stein et al [46]. Horton et al [20] classify performed passes during a soccer match.…”