Tracking futsal players with a wide-angle lens camera: accuracy analysis of the radial distortion correction based on an improved Hough transform algorithm

Abstract

2017) Tracking futsal players with a wide-angle lens camera: accuracy analysis of the radial distortion correction based on an improved Hough transform algorithm, physical education and sport of ribeirão preto, university of são paulo, ribeirão preto, Brazil; b Faculty of pharmaceutical sciences of ribeirão preto, university of são paulo, ribeirão preto, Brazil; c institute of Biosciences, são paulo state university "Júlio de mesquita Filho", rio Claro, Brazil; d departamento de ingeniería electrónica y automática, Ctim (image technology Center), universidad de las palmas de gran Canaria, las palmas de gran Canaria (Canary islands), spain ABSTRACT The aim of this study was to assess the applicability and reliability of a single wide-angle lens GoPro ® camera for tracking and kinematics analysis of futsal players. An official game of a Brazilian professional team in the quarter-final round of the 2013 São Paulo futsal league was recorded by four digital video cameras (30 Hz; 720 × 480) placed at the highest points of the court (40 × 20 m; FIFA standard). We compared tracking performed with three cameras equipped with conventional lenses to a GoPro® camera with a wide-angle lens with a 170° field of view. Manual and automatic tracking of players trajectories (n = 5; 23.20 ± 2.39 years) during competition and in a controlled environment were performed. We found that the root-mean-square error calculated to determine the position on the court based on images captured with a GoPro® camera was 0.32 m and for the velocity was 0.71 m s −1 . A 5-min excerpt of the game showed an average difference of 2.11% between the total distance covered obtained by tracking with the GoPro® with radial distortion correction (438.97 ± 164.65 m), and cameras with conventional lenses (449.54 ± 170.92 m). Temporal correlation analysis confirmed the great similarity between the reconstructed trajectories obtained by these cameras (r = 0.99 for movements on both x and y axes). We showed that a single GoPro® Hero3+ can provide reliable kinematic analysis of computational tracking based on videogrammetry for futsal, using the Hough transform and division model technique for radial distortion correction. ARTICLE HISTORY

Preliminary results on organization on the court, physical and technical performance of Brazilian professional futsal players: comparison between friendly pre-season and official match

“…We chose to use a videogrammetry method based on the DVideo automatic tracking system due to its (i) previous use to obtain the trajectories of professional futsal players (Caetano et al, 2015;Bueno et al, 2014;Milioni, 2014;Moura et al, 2011;Vieira et al, 2015); (ii) low average error (i.e., uncertainties) related to determination of distances covered in a futsal context (0.8 -0.93%) verified in our study and others (Bueno et al 2014, Vieira et al, 2015 or even in soccer (0.3 -1.4%) (Barros et al, 2007;Misuta, 2009;Moura et al, 2012;Moura et al, 2013) and (iii) GPS (Global Positioning System) and LPM (Local Position Measurement), alternative approaches which are capable of quickly obtaining and processing the data of players, i.e., physical performance (Buchheit, Allen, Poon, Modonutti, Gregson, & Di Salvo, 2014;Carling et al, 2008) to obtain almost the same information. However, there are some limitations in capturing displacements in indoor soccer (i.e.…”

“…The 2D data were smoothed using a ButterWorth third-order low pass digital filter with a selected cut-off frequency of 0.4 Hz (Bueno et al, 2014;Vieira et al, 2015). In order to determine the experimental error using the automatic tracking model and filter parameters for data treatment, an experimental protocol was executed where one of the participants was instructed to run for a known distance on the game court (Misuta, 2004;Moura et al, 2013).…”

“…The software DVideo TM Barros et al, 2007;Bueno et al, 2014;Figueroa, Leite, & Barros, 2006a;Vieira et al, 2015) was used for the automatic tracking analysis. Images were synchronized based on common events that occurred in overlapped areas of camera view, such as an instance where an athlete takes the first ball kick in the match or when the ball hits the floor (Bueno et al, 2014;Moura et al, 2013).…”

“…Analysis of match performance based on video recordings in futsal represents an extensive area of investigation (Moore, Bullough, Goldsmith, & Edmondson, 2014), with emphasis on variables related to physical and tactical performances (Bueno et al, 2014;Caetano et al, 2015;Castagna, D'Ottavio, Granda Vera, & Barbero Alvarez, 2009;Corrêa, Alegre, Freudenheim, Dos Santos, & Tani, 2012;Dogramaci, Watsford, & Murphy, 2015;Lapresa, Alvarez, Arana, Garzón, & Caballero, 2013;Makaje, Ruangthai, Arkarapanthu, & Yoopat, 2012;Travassos, Araújo, Vilar, & McGarry, 2011;Vieira et al, 2015;Vilar et al, 2014) and a smaller number of publications related to technical performance (Dogramaci et al, 2015;Gómez, Moral, & Lago-Peñas, 2015;Sarmento et al, 2016). Futsal vigorously taxes both the aerobic and anaerobic metabolism…”

Game Running Performance and Fitness in Women’s Futsal

“…Environmental temperature and relative humidity were around 32 °C and 65 %, respectively. Running data was computed for all players across the game duration using DVIDEOW automatic tracking interface, with average error of 0.14-0.19 m and 0.81-0.93 % to determine static position and distances covered on the court, respectively [26,39].…”