Tackling Similarity Search for Soccer Match Analysis: Multimodal Distance Measure and Interactive Query Definition

Stein, Manuel; Janetzko, Halldór; Schreck, Tobias; Keim, Daniel A.

doi:10.1109/mcg.2019.2922224

Cited by 7 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ideally, player tracking data can be used to learn about and programme the most likely scenarios, but also to produce variants of that scenario to facilitate ‘repetition without repetition’ [ 21 ]. If a player struggles with a particular scenario, either in a match or in the virtual environment, pattern-matching algorithms can be used with large databases of tracking data from actual matches to recognize and recreate similar scenarios [ 70 ]. In this sense, players can be placed into realistic scenarios that originate from actual matches but adapt organically to the movements of the decision maker being trained.…”

Section: Representative Decision Making In Virtual and Augmented Envi...mentioning

confidence: 99%

From Natural Towards Representative Decision Making in Sports: A Framework for Decision Making in Virtual and Augmented Environments

Janssen,

Müller,

Mann

2023

Sports Med

View full text Add to dashboard Cite

Decision making is vital in complex sporting tasks but is difficult to test and train. New technologies such as virtual and augmented reality offer novel opportunities for improving decision making, yet it remains unclear whether training gains using these new approaches will improve decision making on-field. To clarify the potential benefits, a clear conceptualization of decision making is required, particularly for invasive team sports such as football, basketball and field hockey, where decisions are complex with many possible options offered. Therefore, the aim of this position paper is to establish a framework for the design of virtual and augmented environments that help invasive team sport athletes to train their decision-making capacities. To achieve this, we propose a framework for conceptualising ‘natural’ decision making within the performance environment in invasive team sports that views decision making as a continuous cyclical process where the ball carrier interacts with teammates to create ‘windows of opportunity’, and where skilled decision makers often delay decisions to create time, and in turn new opportunities, rather than necessarily selecting the first option available to them. Within the framework, we make a distinction between decision making and anticipation, proposing that decision making requires a series of on-going anticipatory judgments. Based on the framework, we subsequently highlight the consequences for testing and training decision making using virtual and augmented reality environments, in particular outlining the technological challenges that need to be overcome for natural decision making to be represented within virtual and augmented environments.

show abstract

Section: Representative Decision Making In Virtual and Augmented Envi...mentioning

confidence: 99%

From Natural Towards Representative Decision Making in Sports: A Framework for Decision Making in Virtual and Augmented Environments

Janssen,

Müller,

Mann

2023

Sports Med

View full text Add to dashboard Cite

show abstract

“…Analysis of trajectories and trajectory attributes. A series of works from the University of Konstanz proposed methods for clustering trajectories of players during game episodes [27] and segmenting the game, finding interesting game situations [28], [29] and plays of particular configurations [30], analyzing multiple attributes along trajectories [31] and computing features of team coordination [32].…”

Section: Major Approaches To Football Analyticsmentioning

confidence: 99%

Constructing Spaces and Times for Tactical Analysis in Football

Andrienko

Anzer

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

A possible objective in analyzing trajectories of multiple simultaneously moving objects, such as football players during a game, is to extract and understand the general patterns of coordinated movement in different classes of situations as they develop. For achieving this objective, we propose an approach that includes a combination of query techniques for flexible selection of episodes of situation development, a method for dynamic aggregation of data from selected groups of episodes, and a data structure for representing the aggregates that enables their exploration and use in further analysis. The aggregation, which is meant to abstract general movement patterns, involves construction of new time-homomorphic reference systems owing to iterative application of aggregation operators to a sequence of data selections. As similar patterns may occur at different spatial locations, we also propose constructing new spatial reference systems for aligning and matching movements irrespective of their absolute locations. The approach was tested in application to tracking data from two Bundesliga games of the 2018/2019 season. It enabled detection of interesting and meaningful general patterns of team behaviors in three classes of situations defined by football experts. The experts found the approach and the underlying concepts worth implementing in tools for football analysts.

show abstract

“…Users of their system can draw trajectories on a soccer pitch to query for similar trajectories. Stein et al expand upon the previous work by considering more context around the play, such as opposing player trajectories and actions during the play, while allowing for a user to enforce more constraints via the visual analytics system [28]. Their visual interface includes the ability for a user to query player movement and on-ball events by sketching.…”

Section: Related Workmentioning

confidence: 99%