Using Video Analysis and Machine Learning for Predicting Shot Success in Table Tennis

Abstract

Coaching professional ball players has become more and more difficult and requires among other abilities also good tactical knowledge. This paper describes a program that can assist in tactical coaching for table tennis by extracting and analyzing video data of a table tennis game. The here described application automatically extracts essential information from a table tennis match, such as speed, length, height and others, by analyzing a video of that game. It then uses the well known machine learning library "Weka" to learn about the success of a shot. Generalization is tested by using a training and a test set. The program then is able to predict the outcome of shots with high accuracy. This makes it possible to develop and verify tactical suggestions for players as part of an automatic analyzing and coaching tool, completely independent of human interaction.

User-centric Activity Recognition and Prediction Model using Machine Learning Algorithms

“…A dataset consisting the name of activities was generated from a collection of human actions using mapping and word embedding using LSTM algorithms to predict the future activity was implemented in [28]. Some activity prediction works are also found to be vision-based [7], [29], [2]. Alfaifi and Artoli [30] evaluated recent improvements in activity prediction and proposed a 3Dconvolutional neural network model that extracted features and classified them to predict the action by LSTM.…”

A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer)

“…The high scoring nature of basketball enables clubs to go even further and to apply individual shooting efficiency models (Beshai, 2014). Similar shot prediction models were also developed for ice hockey (Macdonald, 2012) as well as for return plays in tennis (Wei et al, 2016) and table tennis (Draschkowitz et al, 2015).…”