An intelligent framework for automatic event detection in robotic soccer games: An auxiliar tool to help coaches improve their teams' performance

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2010

Autores

portela, j (Autor) FEP; abreu, p (Autor) Outra; reis, lp (Autor) FEUP; oliveira, e (Autor) FEUP; garganta, j (Autor) FADEUP

Ata de Conferência Internacional

Título: Proceedings of the 12th International Conference on Enterprise Information Systems

Páginas: 244-249

ICEIS 10

Funchal, Madeira, Portugal, 8 - 12 June, 2010

Indexação

ISI Web of Knowledge - 5 Citações

Scopus - 4 Citações

Outras Informações

ID Authenticus: P-007-WGY

Abstract (EN): In soccer, the level of performance is determined by a number of a complex variables interrelated: technique, tactics, psychological factors and finally, fitness. Because of this, analyzing this information in a real-time, even for soccer experts like professional coaches has become an impossible task. Automatic event detection tools occupy an important role in this reality, although nowadays there isn't any tool capable of producing information capable of helping a professional coach choosing his team strategy for a specific game. In this research project an automatic event detection tool is purposed and, a set of game statistics defined by a group of sports researchers. All the teams present in the 2009 RoboCup tournament have a pass success rate superior to 65%. These statistics provide an interesting viewpoint on how to evaluate a team performance, such as the importance of dominating the opposing team field without losing the control of our own (this can be seen on the top 3 zone dominance statistics). In the future this project will serve as a base for building a Framework capable of simulating a match between two heterogeneous soccer teams and produce reliable information for optimizing the team performance.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6