16 April 2020 in European Journal of Sport Science
In professional soccer, increasing amounts of data are collected that harness great potential when it comes to analysing tactical behaviour. Unlocking this potential is difficult as big data challenges the data management and analytics methods commonly employed in sports. By joining forces with computer science, solutions to these challenges could be achieved, helping sports science to find new insights, as is happening in other scientific domains. We aim to bring multiple domains together in the context of analysing tactical behaviour in soccer using position tracking data. A systematic literature search for studies employing position tracking data to study tactical behaviour in soccer was conducted in seven electronic databases, resulting in 2338 identified studies and finally the inclusion of 73 papers. Each domain clearly contributes to the analysis of tactical behaviour, albeit in – sometimes radically – different ways. Accordingly, we present a multidisciplinary framework where each domain's contributions to feature construction, modelling and interpretation can be situated. We discuss a set of key challenges concerning the data analytics process, specifically feature construction, spatial and temporal aggregation. Moreover, we discuss how these challenges could be resolved through multidisciplinary collaboration, which is pivotal in unlocking the potential of position tracking data in sports analytics.
5 December 2011 in Sports Biomechanics
LMLuiz Eduardo Barreto Martins
Luiz Eduardo Barreto Martins
RARicardo De Oliveira Anido
Ricardo De Oliveira Anido
RBRicardo Machado Leite De Barros
Ricardo Machado Leite De Barros
The purpose of this study was to characterise Brazilian teams' coverage area and spread on the pitch while attacking and defending and to analyse the teams' organisation in tackle and shot on goal situations. We obtained the trajectories of 223 players in eight games with a tracking method. Team area was defined as the area of the convex hull formed by players' positions. Team spread was defined as the Frobenius norm of the distance-between-player matrix. We calculated teams' area and spread over time and in situations of shots on goal (n = 233) and tackles (n = 1,897). While the players attacked, spread and area (median ± confidence interval) ranged from 322.9 ± 0.8 to 387.8 ± 1.0 m and from 905.4 ± 4.4 to 1,407.6 ± 5.5 m2, respectively. On defence, the values were smaller (p < 0.05) and ranged from 283.4 ± 0.9 to 325.8 ± 0.9 m and from 773.8 ± 4.6 to 1,158.4 ± 5.5 m2 for the spread and the area. In defending circumstances, the teams presented a greater area and spread when they suffered shots on goal than when the teams performed tackles. In attacking situations, the teams presented a greater area and spread when they suffered tackles than when they performed shots on goal. The results allowed showing the attacking–defending interaction between Brazilian teams.
30 April 2013 in Journal of Sports Sciences
LMLuiz Eduardo Barreto Martins
Luiz Eduardo Barreto Martins
The purposes of this study were to characterise the total space covered and the distances between players within teams over ten Brazilian First Division Championship matches. Filmed recordings, combined with a tracking system, were used to obtain the trajectories of the players (n = 277), before and after half-time. The team surface area (the area of the convex hull formed by the positions of the players) and spread (the Frobenius norm of the distance-between-player matrix) were calculated as functions of time. A Fast Fourier Transform (FFT) was applied to each time series. The median frequency was then calculated. The results of the surface area time series median frequencies for the first half (0.63 ± 0.10 cycles · min−1) were significantly greater (P < 0.01) than the second-half values (0.47 ± 0.14 cycles · min−1). Similarly, the spread variable median frequencies for the first half (0.60 ± 0.14 cycles · min−1) were significantly greater (P < 0.01) than the second-half values (0.46 ± 0.16 cycles · min−1). The median frequencies allowed the characterisation of the time series oscillations that represent the speed at which players distribute and then compact their team formation during a match. This analysis can provide insights that allow coaches to better control the team organisation on the pitch.
3 July 2014 in Sports Biomechanics
TPTiago Julio Costa Pereira
Tiago Julio Costa Pereira
GMGustavo Damasceno Moreira
Gustavo Damasceno Moreira
+2
The purpose of this study was to measure and characterise the distances covered by Brazilian professional futsal players. The trajectories of 93 players during five matches were obtained using an automatic tracking method. The distances covered were analysed for different game conditions: over the entire game and during the times when the ball was out of play and in play separately. When the entire game was considered, the results showed that there was a reduction in the total distance covered per minute from the first [median ± IQR (interquartile range): 97.9 ± 16.2 m/min] to the second half (median = 90.3 m/min; IQR = 12.0), and when only the in-play time was considered (first half: 136.6 ± 17.2 m/min; second half: 129.2 ± 16.7 m/min). The percentage of distance covered in the standing and walking velocity range was higher in the second half than in the first when considering the entire game (30.8% and 28.0%, respectively) and during the in-play time (19.3% and 16.2%, respectively). In conclusion, this study verified that futsal players reduced the physical performance during the second half.
23 January 2020 in Research in Sports Medicine
The purpose of this study was two-step: (1) classify ball possession (BP) according to the duration and number of passes and (2) identify which tactical variables most discriminate the different BP. We obtained 527 BPs from four official matches of the Brazilian Soccer Championship 2016. Forty-one “notational”, “space occupation”, and “displacement synchronization” predictor variables were used. The BPs were classified into three groups: short (11.07 ± 4.49 s, 1.93 ± 0.99 passes), medium (26.83 ± 7.33 s, 5.41 ± 1.84 passes), long (55.50 ± 14.97 s, 12.11 ± 4.61 passes). Discriminant analysis identified the five most relevant variables to describe each group: coefficient of variation (CV) of the defensive team’s synchronization-Y, CV defensive team´s synchronization-X, successful pass last third, CV distance between offensive team’s centroid and target, mean of the offensive team’s width. The approach highlights important variables and could benefit the description of offensive and defensive game sequences to provide precise knowledge on the process.