Machine Vision-Based Ping Pong Ball Rotation Trajectory Tracking Algorithm.

Because of the overwhelming characteristics of computer vision technology, the trend of intelligent upgrading in sports industry is obvious. Video technical and tactical data extraction, big data analysis, and match assistance systems have caused profound changes to all aspects of the sports industry. One of the important applications is the playback and analysis of sports videos. People can observe the videos and summarize the experience of sports matches, and in this process, people prefer the computers to also interpret and analyze sports matches, which can not only help coaches in postmatch analysis but also design robots to assist in teaching and training. In this paper, we have examined and designed an automatic detection system for ping pong balls, in which the motion trajectory and rotation information of ping pong balls are mainly detected. To achieve this goal, the detection and tracking algorithm of ping pong balls based on deep neural network is used, and better results are achieved on the data set established by ourselves and the actual system test. After obtaining the position of the ping pong ball in the image, the rotation direction and speed of the ping pong ball are calculated next, and the Fourier transform-based speed measurement method and the CNN-based rotation direction detection method are implemented, which achieve better results in the testing of lower speed datasets. Finally, this paper proposes an LSTM-based trajectory prediction algorithm to lay the foundation for the design of table tennis robot by predicting the trajectory of table tennis. Experimental tests show that the proposed system can better handle the ping pong ball tracking and rotation measurement problems.