Fig 1.
The methodology workflow for computing the recurrence plot computation.
From the players' position on the pitch, the convex hull was extracted (A), and then a binary image of the shape was stored (B). From the dilated contours of the shape (C), the Logarithmic function of the cost (areas of the dilated contours) as a function of the dilation radius (D) was determined to calculate the Multiscale Fractal Dimension curve (E). The maximum fractal in each timestamp was stored as a time series from the k timestamps (F) to be represented by recurrence plots of the whole match (G), and during the attacking (H) and defending (I) phases.
Fig 2.
Recurrence plots of the tactical shapes of the teams that presented the lowest (A) and highest (B) values of recurrence rate when the whole match was selected (in black), and the recurrence plots during the attacking (blue) and defending phases (red).
Fig 3.
Recurrence Quantitative Analysis measures (A: Recurrence Rate; B: Determinism; C: Longest diagonal line; D: Average diagonal line length; E: Entropy; F: Laminarity; G: Trapping time) for the whole match, and for the attacking and defending phases.
Table 1.
Summary of the performance indicators of the teams analyzed.
Table 2.
Correlation coefficients and significance between performance indicators and quantitative recurrence analysis measures (significant correlations in bold).