Computer Science Research
Extraction of Human Motion in a Video Sequence
This work uses a model-based approach in acquiring the motion of human body from a video sequence for multimedia application. Compared with various motion-capture systems, using a model can achieve a flexible and low cost acquisition of human motion in the image sequence. We construct a standard 3D articulate human model that has changeable size, color and surface shape to help the matching of the model and the figure in an image sequence. The model can be driven either automatically by program or manually through a graphics interface. We first fit the model to some frames to obtain a personal model of the focused figure. The subsequent matching of the personal model with the images starts from matching key frames. The motion between key frames is predicted and interpolated according to the motion smoothness. The actual traces are verified by color based correlation of the model and images. We test various sequences and it shows that providing a flexible and functional model can achieve a stable extraction of human motion. The image sequence can be any sports, performances, dancing, and famous scenes recorded in old films. The obtained motion parameter sequence can be delivered to any other model to realize a virtual actor.
Project Presented By
Zheng, Jiang Yu
Education Details
| BS: | Computer Science Fudan University 1983 |
| MS: | Control Engineering Osaka University 1987 |
| PhD: | Control Engineering Osaka University 1990 |
Research Interests
Dr. Zheng earned his B.S. degree from Fudan University, China, in 1983, and his M.S. and Ph.D. degrees from Osaka University in Japan in 1987 and 1990, respectively. He was with ATR Communication Systems Research Laboratory as a research associate from 2000-2003. He then worked at Kyushu Institute of Technology, Japan, from 1993 to 2001 as an associate professor. He specializes in the areas of image, vision, graphics, virtual reality, multimedia, and the internet. His current research interests include 3D Modeling, Dynamic Image Processing, scene representation, digital museums, and combining vision with graphics and human interface. Dr. Zheng received 1991 Best Paper Award from the Information Processing Society of Japan for generating the world's first digital panoramic image. He also received the Excellent Paper Award from the Japan Society of Art and Science in 2000 for his development of a graphics tool to extract human motion from video. He is a senior member of IEEE, and adjunct professor in Beijing University, China.
