基于视觉伺服的手部跟踪仿真研究  

Research and simulation of hand tracking based on visual servo

作　　者：刘玉月[1] 吴东苏[1] 顾宏斌[1] 

机构地区：[1]南京航空航天大学民航学院,南京210016

出　　处：《信息技术》2012年第5期9-15,共7页Information Technology

基　　金：国家高技术研究发展计划项目(2007AA01Z306);国家自然科学基金委员会与民航总局联合资助项目(60776812;61039002)

摘　　要：在虚拟现实技术中,手势是人机交互中一个至关重要的直接输入方式,目前能满足人机交互过程中手势输入的方式仅有数据手套,这种方式存在一些缺点,如不能保证交互过程中的无束缚性和自然性,并且需要复杂的标定和安装过程。计算机视觉为获取手部的三维位置提供了一种更加自然且没有接触的方法,但重点在于解决手部跟踪运动过程中的自遮挡问题。分析了基于视觉伺服的手部跟踪技术,并针对Stewart机器人的动力学模型进行了仿真实验,结果表明该方法能够完成利用主动视觉解决手部跟踪运动过程中的自遮挡问题,进行手部跟踪的任务。Direct use of the hand as an input device is an attractive method for providing natural humancomputer interaction （HCI） in the visual-reality technology. Currently, the only technology that satisfies the advanced requirements of hand-based input for HCI is glove-based sensing, which, however, has several draw-backs including that it hinders the ease and naturalness with which the user can interact with the computer controlled environment, and it requires long calibration and setup procedures. Computer vision has the potential to provide much more natural, non-contact solutions. A very challenging problem in this context, which is the focus of this technology, is avoiding self-occlusions. This paper presents the hand tracking technology based on visual servo, and simulation experiment is carried out on the Stewart robot dynamic model; the results show that the method can solve the self-occlusion problem in the process of the active visual solutions to hand tracking movement, and complete hand tracking task.

关 键 词：手部跟踪 自遮挡 主动视觉 STEWART并联机器人 视觉伺服 图像反馈 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] TP273[自动化与计算机技术—计算机科学与技术]