Manuel Stein

Feature-driven visual analytics of soccer data

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.

Director's Cut: Analysis and Annotation of Soccer Matches

For development and alignment of tactics and strategies, professional soccer analysts spend up to three working days manually analyzing and annotating professional soccer matches. In an effort to improve soccer player and match analysis, a visual-interactive and data-analysis support system focuses on key situations by using rule-based filtering and automatically annotating key types of soccer match elements. The authors evaluate the proposed approach by analyzing real-world soccer matches and several expert studies. Quantitative measures show the proposed methods can significantly outperform naive solutions.

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

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 several use cases and collect additional expert feedback. The resulting findings are discussed with subject matter experts.

Visual-Interactive Search for Soccer Trajectories to Identify Interesting Game Situations.

Recently, sports analytics has turned into an important research area of visual analytics and may provide interesting findings, such as the best player of the season, for various kinds of sports. Soccer is a very popular and tactical game, which also attracted great attention in the last few years. However, the search for complex game movements is a very crucial and challenging task. We present a system for searching trajectory data in soccer matches by means of an interactive search interface that enables the user to sketch a situation of interest. Furthermore, we apply a domain specific prefiltering process to extract a set of local movement segments, which are similar to a given sketch. Our approach comprises single-trajectory, multi-trajectory, and event-specific search functions based on two different similarity measures. To demonstrate the usefulness of our approach, we define a domain specific task analysis and conduct a case study together with a domain expert from FC Bayern München by investigating a real-world soccer match. Finally, we show that multi-trajectory search in combination with event-specific filtering is needed to describe and retrieve complex moves in soccer matches.

Dynamic Visual Abstraction of Soccer Movement

Trajectory‐based visualization of coordinated movement data within a bounded area, such as player and ball movement within a soccer pitch, can easily result in visual crossings, overplotting, and clutter. Trajectory abstraction can help to cope with these issues, but it is a challenging problem to select the right level of abstraction (LoA) for a given data set and analysis task. We present a novel dynamic approach that combines trajectory simplification and clustering techniques with the goal to support interpretation and understanding of movement patterns. Our technique provides smooth transitions between different abstraction types that can be computed dynamically and on‐the‐fly. This enables the analyst to effectively navigate and explore the space of possible abstractions in large trajectory data sets. Additionally, we provide a proof of concept for supporting the analyst in determining the LoA semi‐automatically with a recommender system. Our approach is illustrated and evaluated by case studies, quantitative measures, and expert feedback. We further demonstrate that it allows analysts to solve a variety of analysis tasks in the domain of soccer.

Patent retrieval: a multi-modal visual analytics approach

Claiming intellectual property for an invention by patents is a common way to protect ideas and technological advancements. However, patents allow only the protection of new ideas. Assessing the novelty of filed patent applications is a very time-consuming, yet crucial manual task. Current patent retrieval systems do not make use of all available data and do not explain the similarity between patents. We support patent officials by an enhanced Visual Analytics multi-modal patent retrieval system. Including various similarity measurements and incorporating user feedback, we are able to achieve significantly better query results than state-of-the-art methods.

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

Analysts in professional team sport regularly perform analysis to gain strategic and tactical insights into player and team behavior. Goals of team sport analysis regularly include identification of weaknesses of opposing teams, or assessing performance and improvement potential of a coached team. Current analysis workflows are typically based on the analysis of team videos. Also, analysts can rely on techniques from Information Visualization, to depict e.g., player or ball trajectories. However, video analysis is typically a time-consuming process, where the analyst needs to memorize and annotate scenes. In contrast, visualization typically relies on an abstract data model, often using abstract visual mappings, and is not directly linked to the observed movement context anymore. We propose a visual analytics system that tightly integrates team sport video recordings with abstract visualization of underlying trajectory data. We apply appropriate computer vision techniques to extract trajectory data from video input. Furthermore, we apply advanced trajectory and movement analysis techniques to derive relevant team sport analytic measures for region, event and player analysis in the case of soccer analysis. Our system seamlessly integrates video and visualization modalities, enabling analysts to draw on the advantages of both analysis forms. Several expert studies conducted with team sport analysts indicate the effectiveness of our integrated approach.

Enhancing Parallel Coordinates: Statistical Visualizations for Analyzing Soccer Data.

Visualizing multi-dimensional data in an easy and interpretable way is one of the key features of Parallel Coordinate Plots. However, limitations as overplotting or missing density informations have resulted in many enhancements proposed for Parallel Coordinates. In this paper, we will include density information along each axis for clustered data. The main idea is to visually represent the density distribution of each cluster along the axes. We will show the applicability of our method by analyzing the activity phases of professional soccer players. A final discussion and conclusion will complement this paper.

BigGIS: a continuous refinement approach to master heterogeneity and uncertainty in spatio-temporal big data (vision paper)

Geographic information systems (GIS) are important for decision support based on spatial data. Due to technical and economical progress an ever increasing number of data sources are available leading to a rapidly growing fast and unreliable amount of data that can be beneficial (1) in the approximation of multivariate and causal predictions of future values as well as (2) in robust and proactive decision-making processes. However, todays GIS are not designed for such big data demands and require new methodologies to effectively model uncertainty and generate meaningful knowledge. As a consequence, we introduce BigGIS, a predictive and prescriptive spatio-temporal analytics platform, that symbiotically combines big data analytics, semantic web technologies and visual analytics methodologies. We present a novel continuous refinement model and show future challenges as an intermediate result of a collaborative research project into big data methodologies for spatio-temporal analysis and design for a big data enabled GIS.

From game events to team tactics: Visual analysis of dangerous situations in multi-match data

Sport analytics in general and soccer analytics in particular constitute quickly growing markets when it comes to professional analyses and visualizations. From a data analysis research perspective, soccer is a rich source of geospatial and temporal movement data, with high details and a controlled environment. However, soccer movement is complex as its compounds are actions and reactions of two opposing teams with inverse goals. Common analyses performed today are typically oriented towards statistical analysis and considering aggregate measurements. In this work, we propose a set of effective visual-interactive methods for investigating set plays as a first step towards semi-automated analysis of tactic behavior. In our analytic design, we follow the so-called Information-seeking Mantra by Ben Shneiderman by providing overview visualizations, interactive refinements, and detailed analysis views. We take an applied approach in showing case studies that give evidence for the applicability and merits of our proposed techniques.