Real Time Limb Tracking with Adaptive Model Selection

We describe an efficient and robust method of tracking human forearms as skin colored regions. Of special consideration in the design of this system are real-time and robustness issues. We approach this as 2D tracking problem using skin color and edge information. Multiple 2D limb models are used to enhance tracking of the underlying 3D structure. This includes models for lateral forearm views (waving) as well as for pointing gestures. Experiments on test sequences demonstrate the efficacy of this approach