Application of Feature Tracking in a Vision Based Human Machine Interface for XBOX

摘要：

This paper presents a vision based human machine interface (HMI) for the Xbox. It applies feature tracking algorithms to recognize users head gestures and translates them into commands for the game. The pyramidal implementation of Lucas Kanade feature tracking is used to trace the optical flows in a sequence of frames. The experimental results show the feasibility of the proposed vision based interface, which has reasonable performance comparing with the standard game pad.

关键词： Computer Vision Optical Flow Motion Tracking Human Machine Interface Xbox

作者: Mohammadreza Asghari Oskoei Huosheng Hu

作者单位: School of Computer Science and Electronic Engineering University of Essex,Wivenhoe Park,Colchester CO4 3SQ,U.K.

会议类型: 国际会议

会议名称: 2009 IEEE International Conference on Robotics and Biomimetics(2009 IEEE 机器人与仿生技术国际会议 ROBIO 2009)

会议地点: 桂林

会议语种:英文

页码: 1738-1743

在线出版日期: 2009-12-19（万方平台首次上网日期，不代表论文的发表时间）