Developing an Intelligent Table Tennis Umpiring System: Identifying the ball from the scene

Wong, Patrick K. C. (2008). Developing an Intelligent Table Tennis Umpiring System: Identifying the ball from the scene. In: 2008 Second Asia International Conference on Modelling & Simulation, 13-15 May 2008, Kuala Lumpur, Malaysia.




This paper reports further development of an intelligent table tennis umpiring system, of which the idea and plan was previously published at this conference in 2007. Briefly, table tennis is a fast sport. A service usually takes a few seconds to complete but an umpire needs to make many observations and makes a judgment before or soon after the service is complete. This is a complex task and the author believes the employment of videography, image processing and artificial intelligence (AI) technologies could help evaluating the service. The aim of this research is to develop an intelligent system which is able to identify and track the location of the ball from live video images and evaluate the service according to the service rules.
In this paper, the techniques of identifying a table tennis ball from the scene is described and discussed. A number of image processing techniques have been employed to identify and measure the characteristics of the ball. Artificial neural networks have been applied as a classifier. It classifies whether the detected object is not-a- ball, a ball on the palm or a ball in mid air. The system has been tested on 21 still images which contain pictures of ball-like objects, balls on the palm and in mid air. The preliminary results are very promising. Out of 83 objects, 82 have been correctly classified. The system will be further tested on video images once the video is captured and processed.
This paper also discusses the idea of implementing the final system as a multi-agent system, which the author believes it is appropriate for this application because multiple cameras will have to be employed to obtain accurate results.

Viewing alternatives

Download history


Public Attention

Altmetrics from Altmetric

Number of Citations

Citations from Dimensions

Item Actions