Towards 3d hand tracking using a deformable model

In this paper we rst describe how wehave constructed a 3D deformable Point Distribution Model of the human hand, capturing training data semi-automatically from volume images via aphysically-based model. We then show howwe have attempted to use this model in tracking an unmarked hand moving with 6 degrees of freedom (plus deformation) in real time using a single video camera. In the course of this we show how to improve onaweighted least-squares pose parameter approximation at little computational cost. We note the successes and shortcomings of our system and discuss howitmight be improved.