Human Body Posture Inference for Immersive Interaction

Hongxia Li


Abstract

We present an approach for inferring the body posture from a 3D visual-hull representation. We present an appearance based, view-independent, 3D shape description for classifying and identifying human posture using a support vector machine. The proposed global representation allows a robust description of shape that accommodates for variation of the shape of the human body across multiple people.

The proposed method does not require an articulated body model fitted onto the reconstructed 3D geometry of the human body: It complements the articulated body model since we can define a mapping between the observed shape and the learned descriptions for inferring the articulated body model. The proposed method is illustrated on a set of body postures captured by four cameras.


Maintained by Philippos Mordohai