ABSTRACT
A primary goal of virtual environments (VEs) is to provide natural, ef˜cient, powerful, and ªexible interaction for users while navigating, exploring, and communicating. Providing gestural capabilities as an input modality, particularly in the context of multimodal interaction (Jaimes & Sebe, 2005), can help meet these requirements. Human gestures are natural and ªexible and may often be ef˜cient and powerful, especially as compared with alternative interaction modes. This chapter will cover automatic gesture recognition, focusing particularly on computer vision-based techniques that do not require the user to wear extra sensors, clothing, or equipment.
