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

Shuttlecock tracking is required for examining the trajectory of the shuttle-cock in badminton matches. Player Service Fault Detection identifies service faults during badminton matches. The match point scored by players is analyzed by the first referee based on the shuttlecock landing point and player service faults. If the first referee cannot decide, they use technology such as a third umpire system to assist. The current challenge with the third umpire system is based on the high number of marginal errors in predicting the 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 a pre-trained Convolutional Neural Network (CNN), namely Track-Net. The player service fault detection model uses Google MediaPipe Pose. A Random Forest classifier is used to classify the player’s service faults. The framework is trained using the badminton world federation channel dataset. The dataset consists of 100000 images of badminton players and shuttlecock positions. The models are evaluated using a confusion matrix based on loss, accuracy, precision, recall, and F1 scores. Results demonstrate that the optimized TrackNet model has an accuracy of 90%, which is 5% more with 2.84% less positioning error compared to the current state of the art. The player service fault detection model can classify player faults with 90% accuracy using Google MediaPipe Pose, 10% more compared to the Openpose model. The machine learning framework for shuttlecock tracking and player service fault detection is of use to referees and the Badminton World Federation (BWF) for improving referee decision-making.