NiceMeetVR: facing professional baseball pitchers in the virtual batting cage
Proceedings of the 2002 ACM symposium on Applied computing
Detecting dance motion structure through music analysis
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
| Hi-index | 0.00 |
A useful learning system for human motion characters of traditional arts, such as Mai (Japanese classic dance), Kabuki (one of Japan's traditional stage arts), etc., is being developed. In such arts an effective system to pass the tradition down from a top artist to next generations is required. Video contents are generally used to pass the human motions in traditional arts down for non-experts. However, the video contents normally show the human motions as the views from a single direction. If the human motions are presented from orthogonal three-directions at the same time, it comes more useful. So, our learning system produces the three-dimensional human motion by the sequences of views from a single direction in the video contents, then, the motions from any directions can be presented simultaneously with the video contents.In addition, a learner can check the difference in motion between a top artist and him/herself by the producing his/her three-dimensional skeleton motion with our system and the overlapping it with one of the top artist. Here, in the comparison between two different physiques (a top artist and a learner) a simple adjustment method is suggested.In our study standard motion capture processes are employed, but our goal is to develop an original practical training system of performers' motion for beginners in traditional arts. In this paper the developing system is demonstrated for Kyo-mai (Mai originated in Kyoto) as example. The developing system can be useful not only in performing arts but also in industry or in sports.