Title :
Imitating human dance motions through motion structure analysis
Author :
Nakazawa, Atsushi ; Nakaoka, Shinichiro ; Ikeuchi, Katsushi ; YOKOI, Kazuhito
Abstract :
This paper presents a method for importing human dance motion into humanoid robots through visual observation. The human motion data is acquired from a motion capture system consisting of 8 cameras and 8 PC clusters. Then the whole motion sequence is divided into motion elements and clustered into groups according to the correlation of end-effector trajectories. We call these segments ´motion primitives´. New dance motions are generated by concatenating these motion primitives. We are also trying to make a humanoid dance these original or generated motions using inverse-kinematics and dynamic balancing techniques.
Keywords :
humanities; image motion analysis; image segmentation; image sequences; learning by example; legged locomotion; PC clusters; cameras; dance motion generation; dynamic balancing technique; end-effector trajectories; human dance motion imitation; humanoid robots; inverse-kinematics; motion capture system; motion elements; motion primitives; motion sequence; motion structure analysis; visual observation; Artificial intelligence; Cameras; Humanoid robots; Humans; Motion analysis; Motion detection; Performance analysis; Personal communication networks; Robot vision systems; Robotic assembly;
Conference_Titel :
Intelligent Robots and Systems, 2002. IEEE/RSJ International Conference on
Print_ISBN :
0-7803-7398-7
DOI :
10.1109/IRDS.2002.1041652
