II-1-3: Unsupervised gesture recognition system for learning manipulative actions in virtual basketball
| Number | II-1-3 |
| Title | Unsupervised gesture recognition system for learning manipulative actions in virtual basketball |
| Authors |
Divesh Lala (Kyoto Univrersity) Toyoaki Nishida (Kyoto University) Yasser Mohammad (Kyoto University) |
| Abstract | For natural human-agent interaction, the recognition of important gestures to facilitate communication is necessary. Recent advances in technology have made it possible to use the human body as a means for this interaction. In this paper, we combine techniques to create a process flow which can discover and extract a body gesture, create a low-dimensional model, and then use it to recognize body gestures provided in real-time. We show that this technique can be applied to a virtual basketball game, an environment which is highly dynamic and where the variation of gestures is high. Additionally, the number of gesture training samples required can be fairly low. By using this technique, the user is not constrained to execute a gesture in a particular manner. While we apply it to object manipulation tasks, the future plan is to combine this with contextual information to realize important communication acts to be implemented in agents engaging in more high-level interaction. |
| [Link] |
