NORMA eResearch @NCI Library

A Machine Learning Framework for Shuttlecock Tracking and Player Service Fault Detection

Menon, Akshay (2023) A Machine Learning Framework for Shuttlecock Tracking and Player Service Fault Detection. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (4MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (2MB) | Preview


Shuttle Cock tracking is required for examining the trajectory of the shuttle cock. Player service fault analysis identifies service faults during badminton matches . The match point scored by players are analyzed by first referee through shuttle cock landing point and player service faults . If the first referee cannot make decision, they use technology such as a third umpire system to assist . The current challenge with the third umpire system is based on high number of marginal error for predicting match score . This research proposes a Machine Learning Framework to improve the accuracy of Shuttlecock Tracking and Player service Fault Detection . The proposed framework combines a shuttlecock trajectory model and a player service fault model . The shuttlecock trajectory model is implemented using Pretrained Convolutional neural network (CNN) such as Tracknet.The player service fault model uses Google MediaPipe Pose Pre-trained CNN model to classify player service fault using Random Forest Classifier.The framework is trained using the Badminton world federation channel dataset.The dataset consist of 100000 images of badminton player and shuttle cock position ..The models are evaluated using a confusion matrix, loss,accuracy , precision , f1 and recall. The Optimised Track- Net Model has accuracy of 90% with less positioning error for shuttlecock tracking whereas Player service fault detection can classify player fault with 90% accuracy .The combined machine learning algorithm on shuttlecock tracking and player service fault would benefit Badminton World Federation (BWF) for enhancing match score analysis.

Item Type: Thesis (Masters)
Stynes, Paul
Pathak, Pramod
Uncontrolled Keywords: CNN; Tracknet; MediaPipe; Shuttle cock Tracking; Player service fault analysis
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 22 May 2023 10:33
Last Modified: 22 May 2023 10:33

Actions (login required)

View Item View Item