作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2009, Vol. 35 ›› Issue (15): 198-200. doi: 10.3969/j.issn.1000-3428.2009.15.069

• 人工智能及识别技术 • 上一篇    下一篇

基于视线跟踪和手势识别的人机交互

肖志勇,秦华标   

  1. (华南理工大学电子与信息学院,广州 510640)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-08-05 发布日期:2009-08-05

Human-computer Interaction Based on Gaze Tracking and Gesture Recognition

XIAO Zhi-yong, QIN Hua-biao   

  1. (School of Electronic and Information, South China University of Technology, Guangzhou 510640)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-08-05 Published:2009-08-05

摘要: 提出一种新的基于视线跟踪和手势识别的交互方式用于远距离操作计算机。系统通过摄像头采集用户的图像,利用图像识别算法检测人眼和手指的位置,由人眼和指尖的连线确定用户指向屏幕的位置,通过判别用户手势的变化实现各种操作,达到人机交互的目的。实验结果表明,该交互方式可以较好地定位屏幕和判断用户的操作,实现自然、友好的远距离人机交互。

关键词: 人机交互, 视线跟踪, 手势识别

Abstract: This paper presents a novel human-computer interaction for long-distance operation based on gaze tracking and gesture recognition. The system analyzes the image captured by camera and finds the position of eyes and fingers through some recognition algorithms. The position which user points to the screen finds through the line from the eye to the finger. By recognizing user’s gestures, the system executes various operations. Experimental results demonstrate that the interaction can locate the position on the screen and recognize user’s gesture. This method achieves friendly and natural long-distance human-computer interaction.

Key words: human-computer interaction, gaze tracking, gesture recognition

中图分类号: