International Journal of Advances in Computer Science and Its Applications
Author(s) : MASUMI YAJIMA, TAKESHI MATSUDA, TOSHIYUKI MAEDA
This paper addresses sports skill discrimination using motion picture data, focused on volleyball attack skill. We attempt to certify the hypothesis that expert skills have relatively low frequency motions rather than novice skills as the similarity of human postural control. For this purpose we proceed experiments and analyze sports skills as for frequency of motion using time series motion pictures of volleyball attacks. In this paper, volleyball play is analyzed with motion picture data recorded by hi-speed cam-coder, where we do not use physical information such as body skeleton model, and so on. Time series data are obtained from the motion picture data with four marking points, and analyzed using Fast Fourier Transform (FFT) and clustering data mining method. As the experiment results, we have found that y-axes of novice data may have more highfrequency data, and that implies novice motions may have high frequency motions, and that may support our hypothesis.