Application of deep learning in automatic detection of technical and tactical indicators of table tennis
Open Access
- 9 March 2021
- journal article
- retracted article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (3), e0245259
- https://doi.org/10.1371/journal.pone.0245259
Abstract
A DCNN-LSTM (Deep Convolutional Neural Network-Long Short Term Memory) model is proposed to recognize and track table tennis’s real-time trajectory in complex environments, aiming to help the audiences understand competition details and provide a reference for training enthusiasts using computers. Real-time motion features are extracted via deep reinforcement networks. DCNN tracks the recognized objects, and the LSTM algorithm predicts the ball’s trajectory. The model is tested on a self-built video dataset and existing systems and compared with other algorithms to verify its effectiveness. Finally, an overall tactical detection system is built to measure ball rotation and predict ball trajectory. Results demonstrate that in feature extraction, the Deep Deterministic Policy Gradient (DDPG) algorithm has the best performance, with a maximum accuracy rate of 89% and a minimum mean square error of 0.2475. The accuracy of target tracking effect and trajectory prediction is as high as 90%. Compared with traditional methods, the performance of the DCNN-LSTM model based on deep learning is improved by 23.17%. The implemented automatic detection system of table tennis tactical indicators can deal with the problems of table tennis tracking and rotation measurement. It can provide a theoretical foundation and practical value for related research in real-time dynamic detection of balls.Funding Information
- the Science and Technology Project of China Railway Corporation (1341324011)
This publication has 20 references indexed in Scilit:
- Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networksHydrology and Earth System Sciences, 2018
- Deep learning with long short-term memory networks for financial market predictionsEuropean Journal of Operational Research, 2018
- Real-Time Visual Measurement With Opponent Hitting Behavior for Table Tennis RobotIEEE Transactions on Instrumentation and Measurement, 2018
- Research on real – time tracking of table tennis ball based on machine learning with low-speed cameraSystems Science & Control Engineering, 2018
- NEW BUSINESS MODEL IN THE GROWING E-SPORTS INDUSTRYPoslovna izvrsnost - Business excellence, 2017
- Once for All: A Two-Flow Convolutional Neural Network for Visual TrackingIEEE Transactions on Circuits and Systems for Video Technology, 2017
- iTTVis: Interactive Visualization of Table Tennis DataIEEE Transactions on Visualization and Computer Graphics, 2017
- Table tennis match analysis: a reviewJournal of Sports Sciences, 2017
- Match analyses of table tennis in China: a systematic reviewJournal of Sports Sciences, 2017
- Analytic and descriptive approaches to systematic match analysis in table tennisGerman Journal of Exercise and Sport Research, 2017