The purpose of this study is to realize a multi-media sensing system for robot. Using both image and sound processing, the system makes a robot track a person who is speaking. The sound direction is calculated from the phase difference between sounds from two microphones at the right and left ear positions. Then by detecting synchronization between the sound and image changing, the system identifies the speaker. Furthermore, by introducing a multi-level synchronization checking and context analysis, the action pattern of the robot can be regulated to make the robot work in the complicated environment where plural speakers exist. All the processes are performed in real-time. The proposed system is implemented in the information assistant robot 'Hadaly'.
|ホスト出版物のタイトル||Robot and Human Communication - Proceedings of the IEEE International Workshop|
|出版ステータス||Published - 1995|
|イベント||Proceedings of the 1995 4th IEEE International Workshop on Robot and Human Communication, RO-MAN - Tokyo, Jpn|
継続期間: 1995 7 5 → 1995 7 7
|Other||Proceedings of the 1995 4th IEEE International Workshop on Robot and Human Communication, RO-MAN|
|Period||95/7/5 → 95/7/7|
ASJC Scopus subject areas