一种基于加速计的手势识别算法及其在虚拟环境中的应用  

An accelerometer-based gesture recognition algorithm and its application in virtual environment

作　　者：刘剑锋[1] 张大兴[2] 

机构地区：[1]浙江大学CAD&CG国家重点实验室,浙江杭州310058 [2]杭州电子科技大学计算机学院,浙江杭州310018

出　　处：《机电工程》2010年第8期91-96,共6页Journal of Mechanical & Electrical Engineering

基　　金：国家自然科学基金重点资助项目(60533080);国家高技术研究发展计划("863"计划)资助项目(2006AA01Z303)

摘　　要：针对虚拟环境下的三维交互问题,提出了基于加速计的手势识别算法。识别之前先对加速计输出做量化处理,再用离散型隐马尔科夫模型(HMM)进行建模、训练与识别。基于此识别算法,将手势作为一种交互方式应用在三维交互系统中,建立了手势-语义映射表,以训练标准手势,最后对输入手势进行了识别,根据识别结果完成了交互语义。将算法应用于虚拟奥运博物馆实例中,实验结果表明,该算法可有效快速识别出用户输入手势,且平均识别率达到90%以上,用户凭借此方法能准确无误地完成交互。Aiming at the 3D interaction in virtual environment,an accelerometer-based gesture recognition algorithm was proposed.As a pre-process procedure,raw data output by accelerometer was quantized,and then the discrete hidden Markov model（HMM） was used to train and recognize them.Based upon this recognition algorithm,gestures was treated as a method of human-computer interaction and used in 3D interaction subsystem in VR system.The gesture-semantic map was established,the standard gestures was trained,finally the recognition was done.Experimental results show that the system can recognize input gestures quickly with a reliable recogniton rate.The users are able to perform most of the typical interaction tasks in virtual environment by this accelerometer-based device.

关 键 词：三轴加速计 隐马尔科夫模型 手势识别 三维交互 虚拟现实 

分 类 号：TH164[机械工程—机械制造及自动化] TP301[自动化与计算机技术—计算机系统结构]