IEEE-Sensor-Journal-Motion-Recognition-2012

IEEE-Sensor-Journal-Motion-Recognition-2012

ID:39715678

大小:908.03 KB

页数:8页

时间:2019-07-09

IEEE-Sensor-Journal-Motion-Recognition-2012 _第1页
IEEE-Sensor-Journal-Motion-Recognition-2012 _第2页
IEEE-Sensor-Journal-Motion-Recognition-2012 _第3页
IEEE-Sensor-Journal-Motion-Recognition-2012 _第4页
IEEE-Sensor-Journal-Motion-Recognition-2012 _第5页
资源描述:

《IEEE-Sensor-Journal-Motion-Recognition-2012 》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、1166IEEESENSORSJOURNAL,VOL.12,NO.5,MAY2012MEMSAccelerometerBasedNonspecific-UserHandGestureRecognitionRuizeXu,ShengliZhou,andWenJ.Li,Fellow,IEEEAbstract—Thispaperpresentsthreedifferentgesturerecogni-recognitionsystemwhichcanrecognizesevenhandgesturesintionmodelswhicha

2、recapableofrecognizingsevenhandgestures,3-Dspaceisbuilt.Thesystemhaspotentialusessuchasare-i.e.,up,down,left,right,tick,circle,andcross,basedontheinputmotecontrollerforvisualandaudioequipment,orasacontrolsignalsfromMEMS3-axesaccelerometers.Theaccelerationsofahandinmo

3、tioninthreeperpendiculardirectionsaredetectedmechanismtocommandmachinesandintelligentsystemsinof-bythreeaccelerometersrespectivelyandtransmittedtoaPCviaficesandfactories.Bluetoothwirelessprotocol.Anautomaticgesturesegmentational-Manykindsofexistingdevicescancaptureges

4、tures,suchasgorithmisdevelopedtoidentifyindividualgesturesinasequence.Tocompressdataandtominimizetheinfluenceofvariationsre-a“Wiimote,”joystick,trackballandtouchtablet.Someofthemsultedfromgesturesmadebydifferentusers,abasicfeaturebasedcanalsobeemployedtoprovideinputto

5、agesturerecognizer.onsignsequenceofgestureaccelerationisextracted.ThismethodButsometimes,thetechnologyemployedforcapturinggesturesreduceshundredsofdatavaluesofasinglegesturetoagesturecanberelativelyexpensive,suchasavisionsystemoradatacodeof8numbers.Finally,thegesture

6、isrecognizedbycomparingthegesturecodewiththestoredtemplates.Resultsbasedon72ex-glove[8].Tostrikeabalancebetweenaccuracyofcollecteddataperiments,eachcontainingasequenceofhandgestures(totalingandcostofdevices,aMicroInertialMeasurementUnit628gestures),showthatthebestoft

7、hethreemodelsdiscussedisutilizedinthisprojecttodetecttheaccelerationsofhandmo-inthispaperachievesanoverallrecognitionaccuracyof95.6%,withthecorrectrecognitionaccuracyofeachgesturerangingfromtionsinthreedimensions.91%to100%.WeconcludethatarecognitionalgorithmbasedonTh

8、erearemainlytwoexistingtypesofgesturerecognitionsignsequenceandtemplatematchingaspresentedinthispapercanmethods,i.e.,vision-basedan

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。
相关文章
更多
相关标签