Analysis of futsal matches using a single-camera computer vision system
The use of computer systems in sports has increased significantly in the last decade. Consequently, systems have been developed to help each athlete or team quantify their performance, such as distances traveled, speeds attained, and positions where each athlete was on the court or field. In this work, a method based on computer vision is proposed to analyse futsal matches. Videos were acquired using a single camera with a wide-angle lens, which facilitates the installation and calibration process in different matches and arenas. The approach is illustrated through video recordings of Pato Futsal team, from which the athletes were detected, their positions projected from pixels to real world coordinates their trajectories estimated. The generated data visualization aims to help coaches in their physical and tactical analysis.
Z. Niu, X. Gao, and Q. Tian, “Tactic analysis based on real-world ball trajectory in soccer video,” Pattern Recognition, vol. 45, no. 5, p. 1937–1947, 2012.
G. Zhu, C. Xu, Y. Rui, S. Jiang, W. Gao, and H. Yao, “Trajectory based event tactics analysis in broadcast sports video,” Proceedings of the 15th ACM international conference on Multimedia, vol. 5, pp. 58–67, 2007.
R. Moore, S. Bullough, S. Goldsmith, and L. Edmonson, “A systematic review of futsal literature,” American Journal of Sports Science and Medicine, vol. 2, no. 3, pp. 108–116, 2014.
P. J. Figueroa, N. J. Leite, and R. M. Barros, “Tracking soccer players aiming their kinematical motion analysis,” Computer Vision and Image Understanding, vol. 101, no. 2, pp. 122–135, 2006.
M. B. de Oliveira, “Detecção Automática de Jogadores de Futsal Baseada em Vis˜ao Computacional,” 2017, monografia - Curso de Engenharia de Computação, Centro Federal de Educação Tecnológica de Minas Gerais. Belo Horizonte.
P. H. C. d. Pádua, F. L. C. Pádua, and M. T. D. Sousa, “Particle filter-based predictive tracking of futsal players from a single stationary camera,” Brazilian Symposium of Computer Graphic and Image Processing, vol. 2015-Octob, no. August, p. 134–141, 2015.
L. H. P. Vieira, E. A. Pagnoca, F. Milioni, R. A. Barbieri, R. P. Menezes, L. Alvarez, L. G. Déniz, D. Santana-Cedrés, and P. R. P. Santiago, “Tracking futsal players with a wide-angle lens camera: accuracy analysis of the radial distortion correction based on an improved hough transform algorithm,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 5, no. 3, p. 221–231, 2017.
FIFA, Futsal laws of the game 2014/2015. FIFA-Strasse 20, P.O. Box, 8044 Zurich, Switzerland: FIFA, 2014.
J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv, 2018.
J. Redmon, “Darknet: Open source neural networks in c,” 2016. [Online]. Available: http://pjreddie.com/darknet/
R. C. Gonzalez and R. E. Woods, Processamento Digital de Imagens. Av. Ermano Marchetti, 1435 CEP: 05038-001 – S˜ao Paulo – SP: Pearson, 2009.
A. C. Valente, “Análise Comparativa de Compress˜ao de Imagens Fisheye, Retilíneas e Panorâmicas,” 2010, monografia - Curso de Engenharia Elétrica, Universidade de Brasília, Faculdade de Tecnologia. Brasília.
C. C. dos Santos Cavalcanti Marques, “Um Sistema de Calibração de Câmeras,” 2007, dissertação - Mestrado da área de concentração de Computação Gráfica, Universidade Federal de Alagoas, Programa de Pós Graduação em Matemática. Maceió.
M. C. dos Santos, “Revis˜ao de Conceitos em Projeção, Homografia, Calibração de Câmera, Geometria Epipolar, Mapas de Profundidade e Varredura de Planos,” Unicamp, Campinas, Tech. Rep., 2012.
P. Zarchan and H. Musoff, Fundamentals of Kalman filtering: a practical approach. American Institute of Aeronautics and Astronautics, Inc., 2013.
R. E. Kalman, “A new approach to linear filtering and prediction problems,” Journal of basic Engineering, vol. 82, no. 1, pp. 35–45, 1960.
A. Shehata, S. Mohammad, M. Abdallah, and M. Ragab, “A survey on hough transform, theory, techniques and applications,” 02 2015.