Hand Gesture Recognition and Virtual Game Control.pdf

Hand Gesture Recognition and Virtual Game Control.pdf

ID:33832120

大小:1.92 MB

页数:5页

时间:2019-02-28

Hand Gesture Recognition and Virtual Game Control.pdf_第1页
Hand Gesture Recognition and Virtual Game Control.pdf_第2页
Hand Gesture Recognition and Virtual Game Control.pdf_第3页
Hand Gesture Recognition and Virtual Game Control.pdf_第4页
Hand Gesture Recognition and Virtual Game Control.pdf_第5页
资源描述:

《Hand Gesture Recognition and Virtual Game Control.pdf》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、HandGestureRecognitionandVirtualGameControlBasedon3DAccelerometerandEMGSensorsZhangXu,ChenXiang,VuokkoLantzWangKong-qiaoWangWen-hui,YangJi-haiElectronicSci.&Technol.Dept.MultimodalInteractionNokiaResearchCenter,Univ.ofSci.&Technol.ofNokiaResearchCenterNOKIA(CHINA)InvestmentChina,Hefei;PR

2、CHelsinki,FinlandCO.,LTD.,zhx90@mail.ustc.edu.cnVuokko.Lantz@nokia.comBeijing,PRCxch@ustc.edu.cnKongqiao.Wang@nokia.comABSTRACTAcceleration-based(ACC-based)gesturecontrolisusuallyThispaperdescribesanovelhandgesturerecognitionsystemstudiedasasupplementaryinteractionmodality[6].Itiswelltha

3、tutilizesbothmulti-channelsurfaceelectromyogramsuitedtodistinguishnoticeable,largerscalegestureswith(EMG)sensorsand3Daccelerometer(ACC)torealizedifferenthandtrajectoriesofforearmmovements.Withuser-friendlyinteractionbetweenhumanandcomputers.ACC-basedtechniquessomesubtlefingerorhandmoveme

4、ntSignalsegmentsofmeaningfulgesturesaredeterminedfrommaybeignoredwhereaselectromyogram-based(EMG-based)thecontinuousEMGsignalinputs.Multi-streamHiddengesturerecognitiontechniquesusemulti-channelEMGsig-MarkovModelsconsistingofEMGandACCstreamsarenalswhichcontainrichinformationabouthandgest

5、uresofutilizedasdecisionfusionmethodtorecognizehandgestures.varioussizescales.DuetosomeproblemsinherentintheThispaperalsopresentsavirtualRubik’sCubegamethatisEMGmeasurements,includingtheseparabilityandrepro-controlledbythehandgesturesandisusedforevaluatingtheducibilityofmeasurement,thesi

6、zeofdiscriminablehandperformanceofourhandgesturerecognitionsystem.Forasetgesturesetisstilllimitedto4-8classes[1,4].of18kindsofgestures,eachtrainedwith10repetitions,theaveragerecognitionaccuracywasabout91.7%inrealappli-Inordertorealizeanaturalandrobustgesture-basedHCIcation.Theproposedmet

7、hodfacilitatesintelligentandnaturalsystem,theselectionofinputhandgesturesthatarewellcontrolbasedongestureinteraction.discriminablefromeachotherisofcrucialimportance.Con-sideringthecomplementaryfeaturesofACC-andAuthorKeywords:EMG-measurements,webelievethattheircombinationw

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。