Automatic event extraction and video summaries from soccer games

Mortensen, Asgeir; Gaddam, Vamsidhar Reddy; Stensland, Håkon Kvale; Griwodz, Carsten; Johansen, Dag; Halvorsen, Pål

doi:10.1145/2557642.2579374

Cited by 10 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This investigation was based on video and position data made available by Pettersen, Johansen et al [40]. This dataset has seen wide use for a range of studies that cover topics including both performance analytics, image processing, computer vision and machine learning [41][42][43]. The data available contains video recordings and player positioning data for two professional soccer games hosted at Alfheim Stadium in Tromsø, Norway in 2013.…”

Section: Datasets and Processingmentioning

confidence: 99%

Collective states and their transitions in football

2021

View full text Add to dashboard Cite

Movement, positioning and coordination of player formations is a key aspect for the performance of teams within field-based sports. The increased availability of player tracking data has given rise to numerous studies that focus on the relationship between simple descriptive statistics surrounding team formation and performance. While these existing approaches have provided a high-level a view of team-based spatial formations, there is limited research on the nature of collective movement across players within teams and the establishment of stable collective states within game play. This study draws inspiration from the analysis of collective movement in nature, such as that observed within schools of fish and flocking birds, to explore the existence of collective states within the phases of play in soccer. Order parameters and metrics describing group motion and shape are derived from player movement tracks to uncover the nature of the team’s collective states and transitions. This represents a unique addition to the current body of work around the analysis of player movement in team sports. The results from this study demonstrate that sequences of ordered collective behaviours exist with relatively rapid transitions between highly aligned polar and un-ordered swarm behaviours (and vice-versa). Defensive phases of play have a higher proportion of ordered team movement than attacking phases, indicating that movements linked with attacking tactics, such as player dispersion to generate passing and shooting opportunities leads to lower overall collective order. Exploration within this study suggests that defensive tactics, such as reducing the depth or width to close passing opportunities, allows for higher team movement speeds and increased levels of collective order. This study provides a novel view of player movement by visualising the collective states present across the phases of play in football.

show abstract

Section: Datasets and Processingmentioning

confidence: 99%

Collective states and their transitions in football

2021

View full text Add to dashboard Cite

show abstract

“…This query tool allows repeated combinations to be found in a game or across a series of games. Another kind of support for queries is provided in the system Bagadus for finding game events of interest such as "player X is in opponent's 18-yard box", "find all sprints faster than 10 mps" and "a striker is in a 3meters distance from another player" [52]. Retrieved events are accompanied by corresponding videos.…”

Section: Analysis Of Trajectory Attributesmentioning

confidence: 99%

Visual analysis of pressure in football

Andrienko

Budziak

Dykes

et al. 2017

Data Min Knowl Disc

View full text Add to dashboard Cite

Modern movement tracking technologies enable acquisition of high quality data about movements of the players and the ball in the course of a football match. However, there is a big difference between the raw data and the insights into team behaviors that analysts would like to gain. To enable such insights, it is necessary first to establish relationships between the concepts characterizing behaviors and what can be extracted from data. This task is challenging since the concepts are not strictly defined. We propose a computational approach to detecting and quantifying the relationships of pressure emerging during a game. Pressure is exerted by defending players upon the ball and the opponents. Pressing behavior of a team consists of multiple instances of pressure exerted by the team members. The extracted pressure relationships can be analyzed in detailed and summarized forms with the use Keywords Football data analysis • Movement data analysis • Collective movement patterns • Visual Analytics

show abstract

“…The entire system is under constant development, and new functionality is added all the time, e.g., camera-array-wide synchronized automatic exposure [8], interactive zoom and panning [9,10], extended search functionality [22] and scaling the panorama system up to a higher number of cameras and to higher resolution cameras [9]. So far, the pipeline scales nicely with the CPU frequencies, number of cores and GPU resources.…”

Section: Discussionmentioning

confidence: 99%

Processing Panorama Video in Real-time

Stensland

Gaddam

Tennøe

et al. 2014

Int. J. Semantic Computing

Self Cite

View full text Add to dashboard Cite

There are many scenarios where high resolution, wide field of view video is useful. Such panorama video may be generated using camera arrays where the feeds from multiple cameras pointing at different parts of the captured area are stitched together. However, processing the different steps of a panorama video pipeline in real-time is challenging due to the high data rates and the stringent timeliness requirements. In our research, we use panorama video in a sport analysis system called Bagadus. This system is deployed at Alfheim stadium in Tromsø, and due to live usage, the video events must be generated in real-time. In this paper, we describe our real-time panorama system built using a low-cost CCD HD video camera array. We describe how we have implemented different components and evaluated alternatives. The performance results from experiments ran on commodity hardware with and without co-processors like graphics processing units (GPUs) show that the entire pipeline is able to run in real-time.

show abstract

Automatic event extraction and video summaries from soccer games

Cited by 10 publications

References 14 publications

Collective states and their transitions in football

Collective states and their transitions in football

Visual analysis of pressure in football

Processing Panorama Video in Real-time

Contact Info

Product

Resources

About