#IACSS2011: Post Facto

I was not able to blog live from the IACSS Eighth International Symposium of Computer Science in Sport.

Here is my first report of events at the Symposium held at the Shanghai University of Sport.

The program extended over three days. Each daily report is shared as a Word Document.

Day One IACSS11 Day 1

Day Two IACSS11 Day 2

Day Three IACSS11 Day 3

Over the three days of the Symposium there were eight keynote addresses, sixty-one oral presentations and twenty poster presentations.

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 2 Session 1

The Computer Science in Sport Conference (Special Emphasis:Football) at Schloss Dagstuhl on Day 2 had two morning sessions on Dynamical Systems.

Jurgen Perl chaired these sessions and introduced the first presenter in the session, Dietmar Saupe (Universitat Konstanz). Dietmar noted the Wikipedia link to Dynamical Systems. He provided a mathematical introduction to dynamical systems.

The abstract for Dietmar’s presentation is:

Based on a physical model for the forces that must be applied by pedaling while cycling and a simple physiological model for the exertion of the athlete as a function of his/her accumulated power output, an optimal riding strategy for time trials on mountain ascents is computed. A combination of the two models leads to a mathematical optimization problem that can be solved numerically by discretization. The physical model depends most sensitively on an accurate estimation of the road slope on the course. For this purpose, we also present a new method that combines model-based slope estimations with noisy measurements from multiple GPS signals of differing quality. Altogether, we provide a means to analyze rider performance, to identify and quantify potential performance improvement, as well as to instruct the athlete exactly where and how to change his/her pacing strategy to achieve these gains.

He presented a Model-Based Optimisation of Pacing Strategies for Cycling Time Trials (work underway with colleagues Stefan Wolf and Thorsten Dahl) with particular reference to uphill time trials. He used example data from Schienenberg. Dietmar uses power and velocity data combined with GPS and DGPS data to have better estimate the of slope of a climb.

Dietmar discussed Monod and Scherrer’s (1965) and Morton’s (1996) three-parameter Hyperbolc Model and applied these to the Schienenberg simulator rides. Future work in Dietmar’s research group will seek to improve the endurance model, improve the visualisation of proposed velocity during the ride and then test it in the field.

Jaime Sampalo (Universidade de Trás-os-Montes – Vila Real) was the second presenter of the morning session. He discussed GPS data for player positioning in football and their tactical importance. Discussed distance between players in game situations and presented data from a six week intervention study. (See also, Kannekens et al 2011.)

Koen Lemmink (University of Gronigen) was the final presenter of the first morning session. The main focus Koen’s research is performance monitoring during matches and training in ball team sports, like soccer, field hockey, and baskeball. Koen discussed video (SportVU, ProZone, Amisco) and electronic (InMotio LPM, Global Sports) tracking systems and gave an example of the SportVU system at PSV Eindhoven.

Koen shared data from a study reported in Frencken, Lemmink, Delleman and Visscher (2011). The abstract for this paper is:

There is a need for a collective variable that captures the dynamics of team sports like soccer at match level. The centroid positions and surface areas of two soccer teams potentially describe the coordinated flow of attacking and defending in small-sided soccer games at team level. The aim of the present study was to identify an overall game pattern by establishing whether the proposed variables were linearly related between teams over the course of the game. In addition, we tried to identify patterns in the build-up of goals. A positive linear relation and a negative linear relation were hypothesized for the centroid positions and surface areas respectively. Finally, we hypothesized that deviations from these patterns are present in the build-up of goals. Ten young male elite soccer players (mean age 17.3, s=0.7) played three small-sided soccer games (4-a-side) of 8 minutes as part of their regular training routine. An innovative player tracking system, local position measurement (LPM), was used for obtaining player positions at 45 Hz per player. Pearson correlation coefficients were calculated to investigate the proposed linear relation of the key variables. Correlation coefficients indicate a strong positive linear relation during a whole game for the centroid position in all three games, with the strongest relation for the forward-backward direction (r>0.94). For 10 out of 19 goals a crossing of the centroids in this direction can be seen. No negative linear relation was found for surface area (−0.01 < r<0.07). From this study, we concluded that over the course of a whole small-sided game, the forward-backward motion of the centroids is most strongly linearly related. Furthermore, goals show a specific pattern in the forward-backward motion of the centroid. Therefore, surface area and particularly centroid position may provide a sound basis for a collective variable that captures the dynamics of attacking and defending in soccer at team level. Future research should develop these ideas further.

All three presentations stimulated a large number of questions.