The Role of Motion Analysis in Elite Soccer

Carling, Christopher; Bloomfield, Jonathan; Nelsen, Lee; Reilly, Thomas

doi:10.2165/00007256-200838100-00004

Cited by 417 publications

(233 citation statements)

References 42 publications

Supporting

Mentioning

208

Contrasting

Unclassified

Order By: Relevance

“…Its usefulness for coaches and sports analysts needs to be further assessed over multiple matches, with and without professional players. Note, however, that this requires the use of automatic tracking systems, such as AMISCO Pro and ProZone [48]. These systems provide online information to coaches and their staff about players' movements (e.g., energy spent by a player).…”

Section: Practical Remarksmentioning

confidence: 99%

“…Nevertheless, despite of their efficiency and autonomous properties, player-to-player occlusion, similar player appearance, number of players changing over time, variability of players' motion and noises or video blur present themselves as open problems [49]. Therefore, although generally autonomous, these tracking systems still require some human input as well as continual online verification by an operator to make sure that players are correctly tracked by the computer program [48]. Hence, beyond their expensive devices (e.g., many high-definition video cameras), those systems may benefit from the outcome provided by the fractional calculus methodology provided in this paper and previously presented in Couceiro et al [17], to accurately and autonomously estimate a given player's position over time.…”

Section: Practical Remarksmentioning

confidence: 99%

See 1 more Smart Citation

Dynamical Stability and Predictability of Football Players: The Study of One Match

Couceiro

Clemente

Martins

et al. 2014

Entropy

View full text Add to dashboard Cite

Abstract:The game of football demands new computational approaches to measure individual and collective performance. Understanding the phenomena involved in the game may foster the identification of strengths and weaknesses, not only of each player, but also of the whole team. The development of assertive quantitative methodologies constitutes a key element in sports training. In football, the predictability and stability inherent in the motion of a given player may be seen as one of the most important concepts to fully characterise the variability of the whole team. This paper characterises the predictability and stability levels of players during an official football match. A Fractional Calculus (FC) approach to define a player's trajectory. By applying FC, one can benefit from newly OPEN ACCESSEntropy 2014, 16 646 considered modeling perspectives, such as the fractional coefficient, to estimate a player's predictability and stability. This paper also formulates the concept of attraction domain, related to the tactical region of each player, inspired by stability theory principles. To compare the variability inherent in the player's process variables (e.g., distance covered) and to assess his predictability and stability, entropy measures are considered. Experimental results suggest that the most predictable player is the goalkeeper while, conversely, the most unpredictable players are the midfielders. We also conclude that, despite his predictability, the goalkeeper is the most unstable player, while lateral defenders are the most stable during the match.

show abstract

Section: Practical Remarksmentioning

confidence: 99%

Section: Practical Remarksmentioning

confidence: 99%

Dynamical Stability and Predictability of Football Players: The Study of One Match

Couceiro

Clemente

Martins

et al. 2014

Entropy

View full text Add to dashboard Cite

show abstract

“…Métodos tradicionais podem ser morosos e dispendiosos para o clube. A informação rápida e atual é um poderoso diferencial para o time, seus jogadores e a comissão técnica [4].…”

Section: Trabalhos Relacionadosunclassified

“…Por sua vez, o GPS demanda a necessidade de equipamentos acoplados à roupa de cada atleta, além da tecnologia e software compatíveis para a interpretação dos dados [10]. Considerando a disponibilização de dados GPS de jogadores profissionais da primeira divisão do futebol brasileiro pela empresa OneSports 4 , esse estudo tem como proposta validar ou refutar a teoria de que é possível inferir, através de algoritmos de aprendizado de máquina, o posicionamento ideal dos jogadores de futebol através de coordenadas GPS. Os resultados obtidos serão analisados, determinando a viabilidade da aplicação das técnicas propostas.…”

Section: Trabalhos Relacionadosunclassified

“…Segundo [4] é possível determinar a média do desvio padrão de um time, possibilitando assim que as características posicionais sejam analisadas sob essa perspectiva. Nesse estudo, a média do desvio padrão também foi calculada da maneira apropriada, entretanto os resultados obtidos demonstraram-se ineficientes para definir a posição do jogador, uma vez que a variação para algumas posições é muito pequena, gerando um diferencial comparativo muito tênue, conforme pode ser verificado na tabela 7.…”

Section: Análiseunclassified

See 1 more Smart Citation

Análise entre algoritmos de aprendizado de máquina para suportar a predição do posicionamento do jogador de futebol

Gasparini

Álvaro

2017

RBCA

View full text Add to dashboard Cite

Resumo: O esporte de alto desempenho está em busca, cada vez mais, do suporte de tecnologias que visam o auxílio aos atletas e aos profissionais que os acompanham. Atualmente existem diversas tecnologias que são utilizadas no segmento, como análise de deslocamento de jogadores através de GPS (Global Position System), mapeamento através da captura de vídeo, monitoramento de frequên-cia cardíaca, acelerômetro, giroscópio, dentre outros. Entretanto, a comissão técnica possui pouco respaldo tecnológico de ferramentas que consideram as características de movimentação do jogador, as quais poderiam apoiá-las na tomada de decisão em relação ao posicionamento ideal do atleta em campo. Através da coleta de dados de GPS é possível determinar velocidade, distância percorrida, faixas de aceleração, posicionamento, dentre outras informações. Nesse sentido, esse trabalho visa analisar o posicionamento ideal de um jogador de futebol através de algoritmos de aprendizado de máquina, sendo utilizados os modelos de Regressão Logística com Regularização, Redes Neurais e Máquinas de Vetores de Suporte. Os resultados obtidos indicaram que o modelo SVM se sobressaiu aos demais, entretanto são necessários trabalhos futuros para a busca de uma taxa de acerto mais elevada. Palavras-chave:aprendizado de máquina, análise futebolística, gps, máquinas de vetores de suporte, redes neurais artificiais, regressão logística Abstract: The high sport performance is always searching the best technology to support athletes and all professional that helps him. Today there are many technologies in this area, like GPS (Global Position System) motion analysis, video motion analysis, heart rate monitoring, accelerometer, gyroscope and others. The coach has low support from technologies tools that analisys soccer player's characteristics in a game. This informations could help him to decide the ideal position of the athletics. Getting GPS data is possible to define parameters as speed, running distance, acceleration ranges, field positions and others informations. The objective of this study is to find the ideal position for a soccer player using these three machine learning algoritms: Logistic regression with regularization, artificial neural networks and support vector machines. The results show that support vector machines is better than three, but are need future works to find a higher hit rate.Keywords: artificial neural networks, gps, learning machine, logistic regression, soccer analysis, support vector machines 1 Introdução O posicionamento dos jogadores de futebol é, em suma, definido prioritariamente pelo treinador do time. Essa análise e decisão são baseadas inteiramente na percepção do técnico e, em alguns casos, conforme as características anatômicas e antropométricas do atleta [2]. A antropometria é o ramo das ciências humanas que estuda as medidas do corpo, particularmente o tamanho e a forma [1]. Por se tratar de um esporte coletivo é de suma

show abstract

Metabolic Power and Oxygen Consumption in Soccer: Facts and Theories

Osgnach¹,

Prampero

2018

Biomechanics of Training and Testing

View full text Add to dashboard Cite

The Role of Motion Analysis in Elite Soccer

Cited by 417 publications

References 42 publications

Dynamical Stability and Predictability of Football Players: The Study of One Match

Dynamical Stability and Predictability of Football Players: The Study of One Match

Análise entre algoritmos de aprendizado de máquina para suportar a predição do posicionamento do jogador de futebol

Metabolic Power and Oxygen Consumption in Soccer: Facts and Theories

Contact Info

Product

Resources

About