Automated Third Umpire Decision Making in Cricket Using Machine Learning Techniques

No-Balls and run-out play an important part in every cricket. The amount of human error in calling these has been increasing quite heavily over the last few years This wrong decision had a toll on the entire tournament as the team was one win short of qualifying into the knockout stages of the tournament. In this paper, we propose to automate Run-outs and No-Ball delivery’s decision to overcome the human- error made by the umpires. We examine two machine learning techniques - Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) for this purpose and present our results.

[1]  Laurence S. Dooley,et al.  Tracking Table Tennis Balls in Real Match Scenes for Umpiring Applications , 2011 .

[2]  Tariq Mahmood,et al.  A-Eye: Automating the Role of the Third Umpire in the Game of Cricket , 2011, 2011 International Conference on Information Science and Applications.

[3]  Md Shamsur Rahim,et al.  Application of computer vision in Cricket: Foot overstep no-ball detection , 2016, 2016 3rd International Conference on Electrical Engineering and Information Communication Technology (ICEEICT).

[4]  R. Suresh,et al.  Deep learning based image classification on amazon web service , 2018 .

[5]  Tushar Sharma,et al.  Cricket umpire assistance and ball tracking system using a single smartphone camera , 2017, PeerJ Prepr..

[6]  H. Zangl,et al.  Directional human approach and touch detection for nets based on capacitive measurement , 2012, 2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings.

[7]  Aini Hussain,et al.  Computer vision approach to automatic linesman , 2014, 2014 IEEE 10th International Colloquium on Signal Processing and its Applications.

[8]  Jian Di,et al.  Technique of Automatic Judgment of Offside Based on Soccer Video , 2012 .

[9]  Mihai Polceanu,et al.  Real Time Tennis Match Tracking with Low Cost Equipment , 2018, FLAIRS Conference.