Using an Avatar to Develop a System for the Predication of Human Body Pose from Moments

Tracking people using movie sequences is not straightforward because of the human body's articulation and the complexity of a person's movements. In this paper we show how a person's 3D pose can be reconstructed by using corresponding silhouettes of video sequences from a monocular view. Currently, a virtual avatar is used to train the model for inferring the pose and a dierent avatar is used to produce novel examples not in the training set in order to evaluate the approach. The approach was subsequently tested using the silhouettes of a walking person.

• Type: Conference
• Year: 2005
• Where: ACII
• Authors: Song Hu, Bernard F. Buxton
• Keywords: ACII 2005, Human Body Articulation, Person's 3D Pose, Person's Movements