We present our framework that efficiently synchronizes dancing motion of a virtual character according to music input. Two modules have been developed to achieve this. A music server analyzes audio input on the fly and extracts information on music such as tempo, time signature, and beat time. A motion client chooses and displays motion clips according to the music information, by time-warping and synchronizing the start time of motion clips with the music beat time. As a preprocessing step, we construct a database of motion clips using captured dancing motion of a dancer. A PCA-based method is presented to easily identify transiting parts from each motion clip.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2007) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: