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*

作者：刘剑锋1，张大兴2 日期：2010-09-08/span> 浏览：3649 查看PDF文档

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*

刘剑锋1，张大兴2

(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)

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。
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
中图分类号：TH164；TP301
文献标识码：A文章编号：1001-4551(2010)08-0091-06

An accelerometerbased gesture recognition algorithm and its application in virtual environment
LIU Jianfeng1, ZHANG Daxing2
(1. State Key Lab of CAD & CG, Zhejiang University, Hangzhou 310058, China; 2. College of Computer Science, Hangzhou Dianzi University, Hangzhou 310058, China)

Abstract: 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.
Key words: triaxes accelerometer; hidden Markov model(HMM); gesture recognition; 3D interaction; virtual reality