“Characteristic gait animation synthesis from single view silhouette”
Conference:
Type(s):
Title:
- Characteristic gait animation synthesis from single view silhouette
Abstract:
Characteristics of human motion, such as walking, running or jumping vary from person to person. Differences in human motion enable people to identify oneself or a friend. However, it is challenging to generate animation where individual characters exhibit characteristic motion using computer graphics. Our goal is to construct a system that synthesizes characteristic gait animation automatically. As a result, when crowd animation is generated for instance, the motion with the variation can be made using our system. In our system, we first acquire a silhouette image as input data using a video camera. Second, we extract gait feature from single view silhouette. Finally we automatically synthesize 3D gait animation using the method blending a small number of motion data [KOVAR, L et al 2003].This blending weight is estimated using the gait feature automatically.
References:
1. Y. Makihara, R. Sagawa, Y. Mukaigawa, T. Echigo, Y. Yagi, “Gait Recognition Using a View Transformation Model in the Frequency domain”, Proc. of the 9th European Conf. on Computer Vision (ECCV2006), Vol. 3, pp. 96–99, 2006
2. L, Kovar, M, Gleicher, “Flexible Automatic Motion Blending with Registration Curves”, SIGGRAPH2003, pp. 214–224, 2003