Developing an intelligent table tennis umpiring system

The aim of this research is to develop an intelligent system which is able to evaluate table tennis services independently and aid the umpire to make a more accurate decision. Table tennis is a fast sport. A service usually takes one to a few seconds to complete but there are many observations an umpire needs to take and makes a judgment before or soon after the service is complete. This is a complex and time-critical task and the author believes the employment of videography, image processing and artificial intelligence (AI) technologies could help evaluating the service. This paper outlines the idea and the plan of developing an intelligent assistant for table tennis umpire in evaluating services. The system is expected to be able to track the location of the ball from live video images and evaluate the service according to the service rules. In this pilot study, however, the focus is on the development of the techniques, rather than building a complete system. Various videography, image processing and artificial intelligence techniques will be experimented and evaluated. A prototype system is to be built. The system will be compared and tested against the judgements of a human umpire. Both the accuracy and rate of responses will be concerned. The ultimate goal is to further develop the system so that it can umpire and score table tennis matches autonomously. The system may also benefit players who want to have their services evaluated in real time without the need of having a human umpire present.