ABSTRACT
Offside decisions are an integral part of every soccer game. In recent times, decision-making in soccer games, including offside decisions, has been heavily influenced by technology. However, in spite of the use of a Video Assistant Referee (VAR), offside decisions remain to be plagued with inconsistencies. The two major points of criticism for the VAR have been extensive delays in providing final decisions and inaccurate decisions arising from human errors. The visual nature of offside decision-making makes Computer Vision techniques a viable option for tackling these issues, by automating appropriate aspects of the process. However, the lack of a computational algorithm that captures all aspects of the offside rule, lack of an established methodology to computationally represent soccer match scenes in a way that can be utilized by such an algorithm, and the absence of a diverse, comprehensive dataset for testing these methods have stood in the way of research efforts for this problem. This paper precisely addresses each one of these obstacles, in an effort to facilitate further research in this area. The paper presents a computational offside decision algorithm for soccer match images. The methodology for creating a quantitative representation of soccer match images for this offside algorithm has also been presented as a pipeline of Computer Vision tasks. A novel dataset for evaluating this methodology has been presented, which contains a curated selection of soccer match scenes that represent the various challenges that can be faced by a system that aims to aid or automate the task of making offside decisions. Finally, this paper also details the performance of a specific set of Computer Vision tasks used in the presented pipeline, on the given dataset. The proposed system achieves an F1 score of 0.85 on the dataset. The drawbacks and areas of improvements for these methods have also been discussed in an attempt to focus future research on this task. The presented dataset and pipeline implementation code is available at: https://github.com/Neerajj9/Computer-Vision-based-Offside-Detection-in-Soccer
- FIFA. Video assistant referees (var): How does video assistant referee improve the game? fifa.com, 2018.Google Scholar
- Dale Johnson. The ultimate guide to var in the premier league - all your questions answered. Sony ESPN FC, 2019.Google Scholar
- Peter Catteeuw, Bart Gilis, Arne Jaspers, and Johan Wagemans. Training of perceptual-cognitive skills in offside decision making. J Sport Exerc Psychol. 32:845--861., 2010.Google ScholarCross Ref
- Werner F. Helsen, Bart Gilis, and Matthew Weston. Errors in judging 'offside' in association football: Test of the optical error versus the perceptual flash-lag hypothesis. J Sports Sci. 24:1--8., 2006.Google ScholarCross Ref
- Raôul R. D. Oudejans and Frank C. Bakker. How position and motion of expert assistant referees in soccer relate to the quality of their offside judgements during actual match play. Int J Sport Psychol. 36:3--21., 2005.Google Scholar
- Bart Gilis, Werner Helsen, Peter Catteeuw, and Johan Wagemans. Offside decisions by expert assistant referees in association football: Perception and recall of spatial positions in complex dynamic events. journal of Experimental Psychology: Applied, 14(1), 21--35., 2008.Google Scholar
- Sirimamayvadee Siratanita, Kosin Chamnongthai, and Mistusji Muneyasu. Saliency-based football offside detection. 17th International Symposium on Communications and Information Technologies (ISCIT), Cairns, QLD, 2017, pp. 1--4., 2017.Google ScholarCross Ref
- Michael McKinney. The persistence of vision. vision.org, 2005.Google Scholar
- Telegraph Sport. Var in the premier league explained: How does it work, what decisions can be changed and why is it controversial? www.telegraph.co.uk, 2019.Google Scholar
- Chris Nee. Is var causing more problems than it solves? thesetpieces.com, 2019.Google Scholar
- Elliott Jackson. Chris kamara says roberto firmino offside decision 'was made up' as var controversy grows over liverpool incident. www.liverpoolecho.co.uk, 2019.Google Scholar
- Sirimamayvadee Siratanita, Kosin Chamnongthai, and Mistusji Muneyasu. A method of saliency-based football-offside detection using six cameras. Global Wireless Summit (GWS), Cape Town, pp. 127--131., 2017.Google ScholarCross Ref
- Sirimamayvadee Siratanita, Kosin Chamnongthai, and Mistusji Muneyasu. A method of football-offside detection using multiple cameras for an automatic linesman assistance system. wireless personal communications. Wireless Personal Communications., 2019.Google Scholar
- Karthik Muthuraman, Pranav Joshi, and Suraj K. Raman. Vision based dynamic offside line marker for soccer games. arXiv preprint arXiv:1804.06438, 2018.Google Scholar
- Jagjeet Singh. Vision based method for offside detection in soccer. github.com/jagjeet-singh/Vision-based-method-for-offside-detection-in-soccer., 2017.Google Scholar
- Parthasarathi Khirwadkar, Sriram Yenamandra, Rahul Chanduka, and Ishank Juneja. Offside detection system for football. github.com/kparth98/ITSP-Project, 2017.Google Scholar
- Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele. Deepercut: A deeper, stronger, and faster multi-person pose estimation model. European Conference on Computer Vision (ECCV), 2017.Google Scholar
- Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang. Deep high-resolution representation learning for human pose estimation. CoRR, abs/1902.09212, 2019.Google Scholar
- Helmut Neher, Kanav Vats, Alexander Wong, and David A. Clausi. Hyperstacknet: A hyper stacked hourglass deep convolutional neural network architecture for joint player and stick pose estimation in hockey. pages 313--320, 2018.Google Scholar
- Bridgeman Lewis, Volino Marco, Guillemaut Jean-Yves, and Hilton Adrian. Multi-person 3d pose estimation and tracking in sports. June 2019.Google Scholar
- Theagarajan Rajkumar, Pala Federico, Zhang Xiu, and Bhanu Bir. Soccer: Who has the ball? generating visual analytics and player statistics. June 2018.Google Scholar
- Paolo Spagnolo, Nicola Mosca, Massimiliano Nitti, and Arcangelo Distante. An unsupervised approach for segmentation and clustering of soccer players. pages 133--142, 2007.Google Scholar
- Yasushi Akiyama, Rodolfo Garcia Barrantes, and Tyson Hynes. Video scene extraction tool for soccer goalkeeper performance data analysis. 2019.Google Scholar
- Evon M. O. Abu-Taieh and Hamed S. Al-Bdour. A human body mathematical model biometric using golden ratio: A new algorithm. Machine Learning and Biometrics., 2018.Google Scholar
Index Terms
- A Dataset & Methodology for Computer Vision based Offside Detection in Soccer
Recommendations
Automated Offside Detection by Spatio-Temporal Analysis of Football Videos
MMSports'21: Proceedings of the 4th International Workshop on Multimedia Content Analysis in SportsIn this paper, we propose a new automated method to detect offsides from football match videos. The advantage of our method is that it can strictly follow the official offside rules in which the dynamics of play actions are spatio-temporally ...
DeepSportradar-v2: A Multi-Sport Computer Vision Dataset for Sport Understandings
MMSports '23: Proceedings of the 6th International Workshop on Multimedia Content Analysis in SportsAdvanced data collection technologies, computational tools, and sophisticated algorithms have a revolutionary impact on sports analytics on various aspects of sports, from athletes performance to fan engagement. Computer Vision (CV) and Deep Learning (...
A Method of Football-Offside Detection Using Multiple Cameras for an Automatic Linesman Assistance System
AbstractIn offside detection during a football match, afterimage and occlusion confuse the linesman and the referee, and this confusion can cause judgment errors. This paper proposes a method of football-offside detection using multiple cameras in an ...
Comments