Laboratório de Pesquisas Interdisciplinares em Informação Multimídia
SAFT: Vision-Based System to Support Tactical and Physical Analyses in Futsal

This project addresses the development of a vision-based system to support tactical and physical analyses of futsal teams. Those analyses have great value to coaches, sport professionals and players, since they can be used to increase the teams performances, improve training strategies and support decision making processes. Most part of the current analyses in this sport are manually performed, while the existing solutions based on automatic approaches are frequently composed by costly and complex tools, developed for other kind of team sports, making it difficult their adoption by futsal teams. Our system, on the other hand, represents a simple yet efficient dedicated solution, which is based on the analyses of image sequences captured by a single stationary camera used to obtain top-view images of the entire court. We use adaptive background subtraction and blob analysis to detect players, as well as particle filters to track them automatically in every video frame. The system is capable of extracting the distance traveled by each player, his/her mean and maximum speed, as well as generating heat maps that describe players' occupancy during the match. In order to present the data collected, our system uses a specially developed mobile application. This application also provides the segmentation of events of interest (e.g. kicks, goals, passes, among others) during the game. Experimental results with image sequences of an official match and a training match show that our system can provide the data with global mean tracking errors below 40 cm in those sequences, demanding on about 25 ms to process each frame and, thus, demonstrating a high potential to be used by futsal teams to achieve better results in their competitions.

See also

Vídeos

video 3 Minute Research Pitch

Prof. Flávio Cardeal. Fore more information: CV Lattes.

Prof. Marconi Pereira. Fore more information: CV Lattes.

Pedro Pádua. Fore more information: CV Lattes.

Matheus Oliveira. Fore more information: CV Lattes.

Marco Sousa. Fore more information: CV Lattes.

Luís Nascimento. Fore more information: CV Lattes.

© 2016 Piim-Lab - CEFET-MG - Av. Amazonas, 7675 - Nova Gameleira - Belo Horizonte - MG - Brasil | Tel: 55 31 3319-6870