Automatic detection and classification of football players

Color segmentation of images usually requires a manual selection and classification of samples to train the system. This paper presents an automatic system that performs these tasks without the need of a long training, providing a useful tool to detect and identify figures. In real situations, it is necessary to repeat the training process if light conditions change, or if, in the same scenario, the colors of the figures and the background may have changed, being useful a fast training method. A direct application of this method is the detection and identification of football players.

Real-time GPU color-based segmentation of football players

In this paper, we propose a multi-camera application capable of processing high resolution images and extracting features based on colors patterns over graphic processing units (GPU). The goal is to work in real time under the uncontrolled environment of a sport event like a football match. Since football players are composed for diverse and complex color patterns, a Gaussian Mixture Models (GMM) is applied as segmentation paradigm, in order to analyze sport live images and video. Optimization techniques have also been applied over the C++ implementation using profiling tools focused on high performance. Time consuming tasks were implemented over NVIDIA's CUDA platform, and later restructured and enhanced, speeding up the whole process significantly. Our resulting code is around 4-11 times faster on a low cost GPU than a highly optimized C++ version on a central processing unit (CPU) over the same data. Real time has been obtained processing until 64 frames per second. An important conclusion derived from our study is the scalability of the application to the number of cores on the GPU. © 2011 Springer-Verlag.

Audley's Light:Flute and Computer

Performance by Elizabeth McNutt

Key Players and Key Groups in Teams

This paper contributes to the literature on centrality measures in economics by defining a team game and identifying the key players and key groups
in the game. We extend the work of Ballester et al. (Econometrica, 2006) by incorporating a network outcome component in the players' payoff functions and prove that there is a unique interior Nash Equilibrium in pure strategies. We develop a team intercentrality measure based on alternative scenarios that capture the externality created by teammates on each player.

AfterImage:for baroque flute and fixed media

Commissioned by Sonic Arts Network and Huddersfield Contemporary Music Festival with funds from ACGB for Eleanor Dawson (flute)

Dipping Wings:for flute (alto fl), clarinet (bass cot), tpt, vla, vcl, perc and live electronics

commissioned by Ballet Rambert for 60th Anniversary season, choreographer Mary Evelyn, designer Liz Emmanuel. World premiere: Theatre Royal York 03/06/86

The health profile of football/soccer players in Northern Ireland - a review of the uefa pre-participation medical screening procedure.

BACKGROUND:
It is compulsory that domestic football/soccer teams in UEFA competitions organise players' pre-participation medicals. Although screening guidelines have been established, these remain controversial. The findings of medical examinations can have lasting consequences for athletes and doctors. No previous studies have reported UEFA pre-participation screening results in semi-professional footballers. This study aims to further knowledge regarding 'normal' data in this population.

METHOD:
Retrospective audit and analysis of records of pre-season medicals for all male first-team players at one semi-professional Northern Ireland Premiership team between 2009-2012. Medicals were conducted by the club doctor following the UEFA proforma. Height, weight, blood pressure (BP), full blood count (FBC), dipstick urinalysis and resting electrocardiogram (ECG) were conducted by an independent nurse. Only one ECG must be documented during a player's career; other tests are repeated yearly.

RESULTS:
89 medicals from 47 players (6 goalkeepers, 11 defenders, 22 midfielders and 8 attackers; mean age 25.0 years (SD 4.86)) were reviewed. Mean height of the players was 179.3 cm (SD 5.90) with a mean weight of 77.6 kg (SD 10.5). Of 89 urine dipsticks, 7 were positive for protein; all 7 were normal on repeat testing following 48 hours of rest. Of 40 ECGs (mean ventricular rate 61.2 bpm (SD 11.6)), one was referred to cardiology (right bundle branch block; prolonged Q-T interval). No players were excluded from participation.

CONCLUSIONS:
This study provides important information about 'normal' values in a population of semi-professional footballers. Urinalysis showing protein is not uncommon but is likely to be normal on repeat testing.

Fictions

Work in three movements for chamber ensemble of flute (d piccolo, alto flute), clarinet (d bass clarinet), violin, cello, piano written for Stony Brook Contemporary Music Players, Stony Brook University NY USA