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.