北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2012, Vol. 35 ›› Issue (6): 50-54.doi: 10.13190/jbupt.201206.50.lümy

• 论文 • 上一篇    下一篇

基于数据手套和双目视觉技术的虚拟手势及其空间位置跟踪

吕美玉, 侯文君, 陈 军   

  1. 1. 北京邮电大学 自动化学院, 北京 100876;2. 北京邮电大学 网络系统与网络文化北京市重点实验室, 北京 100876
  • 收稿日期:2012-01-17 修回日期:2012-08-28 出版日期:2012-12-28 发布日期:2013-01-07
  • 通讯作者: 吕美玉 E-mail:meiyulv@163.com
  • 作者简介:吕美玉(1971-),女,讲师,E-mail:meiyulv@163.com
  • 基金资助:

    北京邮电大学青年科研创新计划专项项目(2009RC0604);北京邮电大学网络系统与网络文化北京市重点实验室主任基金项目

Technology of Virtual Gesture and Its Space Location Tracking Based on Data Glove and Binocular Vision

LV Mei-yu, HOU Wen-jun, CHEN Jun   

  1. 1. School of Automation, Beijing University of Posts and Telecommunications, Beijing 100876, China;2. Beijing Key Laboratory of Network System and Network Culture, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2012-01-17 Revised:2012-08-28 Online:2012-12-28 Published:2013-01-07
  • Contact: Mei-Yu LV E-mail:meiyulv@163.com

摘要:

基于数据手套技术,搭建了虚拟手势交互系统,实现人手到虚拟手的映射. 对双目视觉中空间点定位模型进行了修改,提出一种基于两垂直摄像头的空间点定位模型,实现了基于双目视觉技术的运动目标位置与姿态跟踪;通过对CamShift算法的改进,提高了运动目标跟踪系统的准确性和自动性,解决了柔性物体的空间姿态捕捉问题. 在VS2008平台上,用VC++和双摄像头搭建了一个虚拟手势交互平台,通过实验,获取了图像及相应的角度与位置信息对照,将虚拟手的位置和姿态与图片相对照,对所提出的方法进行了验证,证明了该方法的有效性.

关键词: 数据手套, 双目视觉, CamShift算法, 空间定位模型

Abstract:

On the base of data glove, a virtual gesture interaction system is put up that realizes the map from mankind hand to virtual hand. The model of space points location in binocular vision is modified and a new model based on two vertically placed cameras is proposed, in which position and posture tracking of moving target by binocular vision are achieved. By modifying camshaft algorithm, the accuracy and automaticity of moving target tracking system are improved, thereafter, the problem of capturing space posture of flexible object is solved. By comparing the pose and position information of virtual hand with image, the algorithm is testified and approved to be applicable.

Key words: data glove, binocular vision, CamShift algorithm, spatial orientation model

中图分类号: