Ask a tennis table coach to explain what he thinks about his job. This is not something that everyone can do in life. You need to have a precise tactic and a strategic gaming vision.
Three researchers of the Research Group Entertainment Computing, Faculty of Computer Science, the University of Vienna, have deepened the method to improve the coaching performance for tennis table. Lukas Draschkowitz, Christoph Draschkowitz, Helmut Hlavacs presented their study during Intetain 2014 -6th International Conference on Intelligent Technologies for Interactive Entertainment in Chicago, USA. They used an application that automatically extracts essential information from a table tennis match such as speed, length, height and others, by analyzing a video of that game.
The extant studies carried out in this area use the well-known Hawk Eye method. The value added of the new method consists in the use of the application that enhances coaching techniques, instead of being made for the public. As the three academics affirm: “We introduce a simple algorithm that allows to fully automatically analyze a table tennis game by two calibrated off-the-shelf USB webcams, and a laptop using Java and the “OpenCV” and “Weka” libraries. We show that this low-cost setup already results in excellent results, and it may be expected that professional equipment would result in even higher accuracy”.
The study does not detract the importance of the player, which is obviously the center of the game with its successes and failures. The innovative thing is that machine learning can be used to better understand the game techniques, and individual behavior can surely improve training and tactical analysis for individual players.