Computer vision-based gesture recognition for an augmented reality interface

Wearable computing and Augmented Reality applications call for less obtrusive and more intuitive human computer interfaces than keyboards and mice. One way to realise such interfaces is using gestures. e.g., for pointing in order to replace the mouse. The less obtrusive way of gesture recognition is to use computer vision based methods. This paper presents a computer vision-based gesture interface that is part of an Augmented Reality system. It can recognise a 3D pointing gesture, a click gesture, and five static gestures. A lookup-table based colour segmentation and a fast gesture recognition method are presented that enable for 25Hz performance on a standard PC.