Quantifying the value of sprints in elite football using spatial cohesive networks

Date

2020-10-01

Author

Külah, Emre
Alemdar, Hande

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

181
views

0
downloads

Football players are on the move during games and the sprint is one of the distinctive type of those movements. In this study, we focus on quantifying the value of the sprints using the spatial data of players and the collective movements of the teams during the game. We first propose a method to quantify the dispersion of the teams, namely, the weighted team spread. In order to find the weights of the team spread, we use individual players’ interaction behavior, using spatial cohesion matrices. Spatial features of the pitch such as the pitch value and the pass probability value are also used together with the weighted team spread to quantify the value of the sprints. These models are used to understand sprint character of the players according to their role and teams’ collective movements depending on their tactics. The proposed method applied on 306 Turkish first division games from 2018/2019. The sprint analysis results show that attackers have greater sprint averages than midfielders and defenders based on 5498 sprints from corresponding games. Full-backs and attacking midfielders are positions with the best sprint averages other than attacking players. Center backs and defensive midfielders are the weakest positions in sprinting. The results further show that the teams that are focused on having the possession of the ball have less average sprint value than teams playing counter-attack style.

Subject Keywords

Team sport, Sprint analysis, Collective movement, Data mining, Performance analysis

URI

https://hdl.handle.net/11511/47524

Journal

Chaos, Solitons and Fractals

DOI

https://doi.org/10.1016/j.chaos.2020.110306

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Spatio-temporal cohesive networks for evaluating team behavior in soccer Külah, Emre; Alemdar, Hande; Department of Computer Engineering (2019) In this thesis, we analyze positional organizations of soccer teams during game transitions which end with an important result and individual sprinting performances of soccer players. Social networks and distance matrices of teams are used to obtain organizations of teams. Spatial features of pitch such as pitch value and pass probability value are used to evaluate sprint performances. Social networks that we call cohesion matrices are used as weights in both attacking and defending transitions. The norm of...
Prediction of the Ball Location on the 2D Plane in Football Using Optical Tracking Data Amirli, Anar; Alemdar, Hande (2022-01-01) Tracking the ball location is essential for automated game analysis in complex ball-centered team sports such as football. However, it has always been a challenge for image processing-based techniques because the players and other factors often occlude the view of the ball. This study proposes an automated machine learning-based method for predicting the ball location from players' behavior on the pitch. The model has been built by processing spatial information of players acquired from optical tracking dat...
Prediction of the Ball Location on the 2D Plane in Football Using Optical Tracking Data Amirli, Anar; Alemdar, Hande (2022-01-01) Tracking the ball location is essential for automated game analysis in complex ball-centered team sports such as football. However, it has always been a challenge for image processing-based techniques because the players and other factors often occlude the view of the ball. This study proposes an automated machine learning-based method for predicting the ball location from players' behavior on the pitch. The model has been built by processing spatial information of players acquired from optical tracking dat...
Evaluation of Image Representations for Player Detection in Field Sports Using Convolutional Neural Networks Sah, Melike; Direkoglu, Cem (2018-08-28) Player detection is an important task in sport video analysis. Once players are detected accurately, it can be used for player tracking, player activity/performance analysis as well as team activity recognition. Recently, convolutional Neural Networks (CNN) became the state-of-the-art in computer vision for object recognition. CNN based methods usually use gray or RGB images as an input. It is also possible to use other image representation techniques such as shape information image and polar transformed sh...
The Effects of Rhythm Training on Tennis Performance Söğüt, Mustafa; Kirazcı, Sadettin (Walter de Gruyter GmbH, 2012-06-01) Rhythm training is an integral part of sports. The purposes of the study were to analyze the effects of rhythm training on tennis performance and rhytmic competence of tennis players, to compare the improvement levels of tennis specific and general rhythm training and to examine the effects of shorter and longer tempos on rhythmic competence. Thirty university students whose mean score of International Tennis Number (ITN) was 7.3 (+/- 0.9) were divided randomly into three sub-groups: Tennis Group, General R...

Citation Formats

E. Külah and H. Alemdar, “Quantifying the value of sprints in elite football using spatial cohesive networks,” Chaos, Solitons and Fractals, pp. 0–0, 2020, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/47524.