2021/04/20 by Kaustubh Milind Kulkarni, Kulkarni, Kaustubh Milind, Sucheth Shenoy +1 · 3 citations
Medicine · Psychology · #Sports Performance and Training #Sports injuries and prevention #Sport Psychology and Performance
paper · pdf · doi:10.48550/arxiv.2104.09907
We introduce a novel method for collecting table tennis video data and\nperform stroke detection and classification. A diverse dataset containing video\ndata of 11 basic strokes obtained from 14 professional table tennis players,\nsumming up to a total of 22111 videos has been collected using the proposed\nsetup. The temporal convolutional neural network model developed using 2D pose\nestimation performs multiclass classification of these 11 table tennis strokes\nwith a validation accuracy of 99.37%. Moreover, the neural network generalizes\nwell over the data of a player excluded from the training and validation\ndataset, classifying the fresh strokes with an overall best accuracy of 98.72%.\nVarious model architectures using machine learning and deep learning based\napproaches have been trained for stroke recognition and their performances have\nbeen compared and benchmarked. Inferences such as performance monitoring and\nstroke comparison of the players using the model have been discussed.\nTherefore, we are contributing to the development of a computer vision based\nsports analytics system for the sport of table tennis that focuses on the\npreviously unexploited aspect of the sport i.e., a player's strokes, which is\nextremely insightful for performance improvement.\n