A human motion analysis using the rhythm - A estimate method of dance motion with autoregressive model

On our studies, we have focused on japanese traditional dance recorded in image database. In this study, me aims to reproduce the japanese traditional dance motion recorded in image database. We proposes a estimate method of dance motion with the autoregressive model. On statistical motion estimation with the autoregressive model, the decision of degree is a very important. To decide the suitably degree, we define the word of "Rhythm Points" or the time of the start and the end of the motion. And, we called "the cycle of the every motion" or a number of the frame between three rhythm points. To compare our method to others, we applied two methods to get the degree to make the feedback. The first method decided the degree from AIC (Akaike Information Criterion). The second method, which we proposed decided the degree from the cycle of the motion. We introduced term of the decision of suitably degree for a estimate method of dance motion and get good result about an estimate of dance motion.