port action mining: Dribbling recognition in socce

Autor(es)

Barbon Junior, Sylvio ^[1] ; Pinto, Allan ^{[2, 3]} ; Barroso, Joao Vitor ^[1] ; Caetano, Fabio Giuliano ^[4] ; Moura, Felipe Arruda ^[4] ; Cunha, Sergio Augusto ^[3] ; Torres, Ricardo da Silva ^[5]

Afiliação do(s) autor(es)

^[1] Londrina State Univ UEL, Dept Comp Sci, Londrina, Parana - Brazil

^[2] Univ Campinas UNICAMP, Inst Comp, Campinas, SP - Brazil

^[3] Univ Campinas UNICAMP, Sch Phys Educ, Campinas, SP - Brazil

^[4] State Univ Londrina UEL, Sport Sci Dept, Londrina, Parana - Brazil

^[5] NTNU Norwegian Univ Sci & Technol, Dept ICT & Naural Sci, Alesund - Norway

• Tipo de documento: Artigo Científico
• Fonte: MULTIMEDIA TOOLS AND APPLICATIONS; v. 81, n. 3 DEC 2021.
• Citações Web of Science: 0

Resumo

Recent advances in Computer Vision and Machine Learning empowered the use of image and positional data in several high-level analyses in Sports Science, such as player action classification, recognition of complex human movements, and tactical analysis of team sports. In the context of sports action analysis, the use of positional data allows new developments and opportunities by taking into account players' positions over time. Exploiting the positional data and its sequence in a systematic way, we proposed a framework that bridges association rule mining and action recognition. The proposed Sports Action Mining (SAM) framework is grounded on the usage of positional data for recognising actions, e.g., dribbling. We hypothesise that different sports actions could be modelled using a sequence of confidence levels computed from previous players' locations. The proposed method takes advantage of an association rule mining algorithm (e.g., FPGrowth) to generate displacement sequences for modelling actions in soccer. In this context, transactions are sequences of traces representing player displacements, while itemsets are players' coordinates on the pitch. The experimental results pointed out the Random Forest classifier achieved a balanced accuracy value of 93.3% for detecting dribbling actions, which are considered complex events in soccer. Additionally, the proposed framework provides insights on players' skills and player's roles based on a small amount of positional data. (AU)

• Processo FAPESP: 18/19007-9 - Descobrindo séries temporais dos dribles em um cenário físico-tático-técnico durante jogos profissionais oficiais
• Beneficiário: Sergio Augusto Cunha
• Modalidade de apoio: Bolsas no Exterior - Pesquisa
• Processo FAPESP: 19/17729-0 - Abordagens conduzidas por dados para análise de partidas de futebol: uma perspectiva de e-Science
• Beneficiário: Paulo Roberto Pereira Santiago
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/16253-1 - Desvendando o segredo do futebol Brasileiro e Holandês, capturando elementos de estilo de jogo e estratégias de sucesso
• Beneficiário: Allan da Silva Pinto
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 16/50250-1 - O segredo de jogar futebol: Brasil versus Holanda
• Beneficiário: Sergio Augusto Cunha
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 17/20945-0 - EMU concedido no processo 16/50250-1: local positioning system
• Beneficiário: Sergio Augusto Cunha
• Modalidade de apoio: Auxílio à Pesquisa - Programa Equipamentos Multiusuários
• Processo FAPESP: 19/22262-3 - Reconstrução em grande volume: sistema de alta precisão para detecção de posição em esportes
• Beneficiário: Paulo Roberto Pereira Santiago
• Modalidade de apoio: Auxílio Organização - Reunião Científica