Dagstuhl: Day 3 Sessions 1 and 2

Today is the final day of the Computer Science in Sport Conference (Special Emphasis:Football) at Schloss Dagstuhl. The morning session discussed Media and Data Acquisition issues. The session was chaired by Daniel Link (TU Munchen).

Daniel presented first in this session. He reported on the Game Data Library Project for the Bundesliga.

The aims of the Project are:

  • Technical: better data validation and better IT infrastructure
  • Commercial

Daniel discussed the game observation process for the Game Data Library. This involves the acquisition of basic data that includes match information data, tracking data (at 25hz), event data, static video data that are used to create raw data and statistics. Daniel presented the architecture of this service to provide data flow.

He discussed the Game Data Model. Daniel presented an ontology of definitions in use in this project. This ontology has a data structure for: smart calculation; efficient processing and storing of data; and object orientation and the use of Unified Modelling Language (UML).

Daniel concluded his talk with a consideration of the challenges of this project for sport science. These included how to use the enormous amounts of data that will be generated and how to develop tools to analyse the data.

Roland Leser (Universitat Wien) was the second presenter in the session.

His topic was Position tracking as a challenge in game sport analysis. Roland’s abstract:

About 10 to 15 years ago only top level teams used computer assisted video annotation systems to analyze sport games and training sessions. The progress in hardware and software development made it happen that nowadays this technique is used even at amateur level. Pointing to another analysis technique we have at present similar conditions than in the situation described above. Very expensive video based position tracking systems are used by few of the top teams worldwide to analyze their game play and GPS-systems are applied to analyze training sessions of outdoor sports. Radio wave based tracking systems are currently not wide spread for performance analysis but they could dominate the future. By tendency radio wave sensors become smaller and cheaper in the next years and radio wave based tracking systems are much less service intensive than other systems. Looking forward, this kind of tracking system could be a worthwhile alternative to analyze games and training sessions of game sports for many teams. This presentation gives an overlook on the preparatory work of installing an industrial radio wave based tracking system (www.ubisense.net) for game sports analyses, outlines current results and looks ahead to future works.

In his talk Roland gave an excellent exposition of how to develop a position tracking system.

He noted systems such as Tracab and Catapult. He discussed radio wave systems too, including Ubisense (tag) and InMotio LPM (transponder).

In choosing a system for use in his research Roland identified these criteria:

Off the shelf availability of a system:

  • Price
  • Sensor size
  • Sampling rate
  • Accuracy
  • Robustness (hardware, signal, definition of player)
  • Application in training and game play
  • Opponent agreement within competition

Roland discussed the use of an Ubisense system. To date this system has not been used extensively in sport. He demonstrated the installation of the system in a sports hall. Ubisense has a 160hz facility that is not common with other Ubisense clients. The hall is calibrated and then checked for accuracy of measurement. The system allows some for data filtering (low pass and Kalman). Roland noted the development of software tools for the system to enable data visualisation (including heat maps) and performance analysis.

Roland shared an example of the recording movement with the system (small sided football).

The final presentation of the morning was by Malte Siegle. Malte looked at the accuracy of image recognition in dynamic situations. He shared the development of protocols to check the accuracy of image recognition in respect of Laveg and laser light measurement.

The field tests were conducted in a soccer stadium:

1. A linear run near the cameras with constant velocity. (Image detection worked well.)

2. Acceleration, stop, reacceleration in same direction. (Image detection issues arise with up to 1 metre error.)

3. Two players move towards each other and return after 180 degrees turn.  (An error of more than 1.5 metres.)

4. Circular run with constant velocity (Image detection worked well.)

Malte noted the variability in errors in these tests and discussed the impact of the player’s distance from the cameras.

Theses tests had identified the need for better static position detection and the clear differentiation of error sources (distractions). Malte did end with some very positive views about the protocols: good values were recorded and problems were identified. This research raised the possibilities of a new standard in the evaluation of image detection. Ultimately this will lead to the comparisons of different image detection systems.

The final session of the day was chaired by Martin Lames. This was an informal review and evaluation of the Conference. Everyone agreed that the Dagstuhl experience was outstanding and all participants hoped to have the privilege of returning.

Dagstuhl: Day 1 Session 3

The Computer Science in Sport Conference (Special Emphasis:Football) at Schloss Dagstuhl had a mixed group of presentations in the third session of Day 1.

Malte Siegle was the first presenter in the session and discussed his work with Martin Lames on Game Interruptions in football – a neglected element for modelling the demands if the game. Malte introduced his paper with a consideration of  the use of position detection systems to measure performance in football.

He noted that these systems provide no data about game interruptions. In his presentation he shared an analysis of 1729 interruptions in 16 matches and discussed the time, type, location and duration these interruptions. He used Amisco System data to provide more detail about player performance in these games.

Malte noted that interruptions in play were not as long as ball in play. These interruptions were located between intermittent bouts of high intensity match time (most of which were not more than a minute in length before the next interruption). He noted that:

  • There was an average of 108 interruptions per match: these ranged from 0.13% (penalties) to throw in at 39.69% of all interruptions.
  • The average duration of these interruptions ranged from a throw in at 9 seconds to injury at 82.5 seconds.

Malte then made some very important observations about how the place where the interruption takes place affects the length of interruption. He provided some interesting data comparing attacking and defending throw ins. He noted too that direct free kicks in offensive areas with a direct shot at goal opportunity take longer and can reach an average of 36.59 seconds.

Malte indicated that the state of play (winning, losing, drawing) has an impact of the length of interruptions. A team winning can take up an additional 3 seconds on goal kicks and up to 5 seconds on free kicks. This tendency for winning teams to take longer over interruptions becomes even more noticeable towards the end of the game (particularly in relation to throw ins).

Malte concluded his presentation with data about distance travelled in uninterrupted and interrupted games. He used Amisco data to provide detail of these distances. Malte noted that there was evidence that goalkeepers run more in interrupted play and central defenders less.  Malte’s final point was an invitation to consider how interruptions might be used for player recovery and that this recovery may vary within a team depending on a player’s positional responsibilities.

Some recent publicity about Malte’s and Martin’s work can be found here and here.

The second presentation of the session was made by Josef Wiemeyer and was titled Offside and the Wembley Goal – Or can Computer Science help overcome erroneous decisions in Soccer?

The abstract for Josef’s paper was:

The field of sport practice is full of interesting phenomena that lead to uncertainties and sometimes annoyance. Sport science is able to uncover the reasons for these phenomena and to develop solutions. Two phenomena in soccer are a persistent threat to fairness und equal chances in soccer: Erroneous offside decisions (Reasons: perspective and synchronous visual perception, flash-lag effect) according to research about 20 to 25% of offside decisions are wrong! Erroneous goal decisions (Reason: depth perception and stereoscopic vision) Using these two examples the question arises if and how computer science can help to improve the situations of the referees in soccer. In the past, selected options have been suggested to solve these problems. This statement emphasizes the strong support computer science in sport can give to solve persistent issues in soccer practice. Referees and their assistants are systematically overloaded by the perceptual demands in offside and goal decision situations. Information technologies should support them to ensure a maximum level of fairness and equal chances.

In his presentation, Josef noted:

  • 20-25% offside decisions are wrong.
  • 80% of these are false alarms
  • Decisions about offside are affected by synchronous optic perception (Gralla et al., 2007, Sachsenweger, 1987))

Josef indicated the role training of synchronous optic perception can play in improving decision making. However there is no evidence of the longer term affects of this training (experimental trials last six weeks) and there is still the issue of dealing with moving stimuli reported by Oudejans et al. (2000) and the Hazelhoff flash lag effect discussed by Baldo et al. (2002).

Josef discussed three solutions to these problems: training, technology, and changing the rules.

Josef then extended his discussion to the arbitration of goal line technology and used  examples of ‘goals’ from 1966 and 2010 (Germany v England). He provided details of FIFA and IFAB discussions around goal line technology.

He concluded his presentation with an invitation to delegates to consider transparency, justice and fairness in decision making by officials.

Karen Roemer presented the third paper of this session and invited delegates to discuss the design options for a longitudinal study of female athletes’ ACL injuries (including female football, basketball and volleyball players).

Karen noted that most research into ACL injury is mostly retrospective. She is keen to plan a prospective study. She noted this study:

Arnold Baca (Universitat Wien) followed Karen’s presentation with a discussion of the development of  a mobile coaching system (Mobile Coach 1.0). Arnold’s abstract for the paper was:

A wireless system for monitoring, transmitting and processing performance data in sports for the purpose of providing feedback has been developed. Experts are provided with remote data access, analysis and (partly automated) feedback routines. In this way, they are able to provide athletes with individual feedback from remote locations. One specific sport, the system could be utilized for, is football.

Arnold noted the feedback potential of this system for elite and mass participation applications. Two papers detail the development of this work: Baca et al (2009, 2010).

Josef Wiemeyer concluded the session with a discussion of Serious Games New options for learning and training in sport and noted some of the important contributions to the literature (Burdea, 2003; Rigby & Przyglski 2009; Hays 2005; Susi et al 2007; Bavelier 2010).

He discussed the role serious games can play in health promotion (Lieberman 1997) and their growing use in exergaming. He sounded a note of caution about the energy expenditure in such games and discussed the relative small transfer of skills from games to real life sport.

Josef’s work in this area can be found in two recent papers (Liem and Wiemeyer, 2010: a study of balance training; and Wiemeyer and Scheider, 2011: Basketball.)

He concluded with  Fritz’s  (2006) observation that “games support what they demand”. He encouraged delegates to consider the role serious games can play in improving: sensory motor activity; cognition; motivation, emotion, volition; social competency; and media competency.

The session concluded at 6 p.m.

Dagstuhl: Day 1 Session 1

The Computer Science in Sport Conference (Special Emphasis:Football) started at Schloss Dagstuhl this morning.

Martin Lames is coordinating the Conference.

There is a list of participants here.

The first session was an introduction to Dagstuhl and to the Conference program.

Themes of the Conference include:

All these will take place in the context of the wonderful social environment of Dagstuhl and a number of unmeetings.

(A note about unmeetings (via Jay Cross):

New approaches create meetings that people enjoy, often organized in scant time, at minimal cost. Unconferences are characterized by:

  • No keynote speaker or designated expert
  • Breakthrough thinking born of diversity
  • Having fun dealing with serious subjects
  • Emergent self-organization
  • Genuine community, intimacy and respect)