Computer vision-based gesture recognition for an augmented reality interface

被引：0

作者：

Störring, M ^{[1
]}

Moeslund, TB ^{[1
]}

Liu, Y ^{[1
]}

Granum, E ^{[1
]}

机构：

[1] Aalborg Univ, Comp Vis & Media Technol Lab, DK-9220 Aalborg, Denmark

来源：

PROCEEDINGS OF THE FOURTH IASTED INTERNATIONAL CONFERENCE ON VISUALIZATION, IMAGING, AND IMAGE PROCESSING | 2004年

关键词：

computer vision; face and gesture recognition; human-computer interaction; augmented reality;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：766 / 771

页数：6