基于多特征信息的疲劳驾驶检测系统分析

基于多特征信息的疲劳驾驶检测系统分析

ID:33005595

大小:1.55 MB

页数:69页

时间:2019-02-19

基于多特征信息的疲劳驾驶检测系统分析_第1页
基于多特征信息的疲劳驾驶检测系统分析_第2页
基于多特征信息的疲劳驾驶检测系统分析_第3页
基于多特征信息的疲劳驾驶检测系统分析_第4页
基于多特征信息的疲劳驾驶检测系统分析_第5页
资源描述:

《基于多特征信息的疲劳驾驶检测系统分析》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库

1、基于多特征信息的疲劳驾驶检测系统研究AbstractAsweknow,fatiguedrivinghasbecome"thenumberonekiller"oftrafficsafety,andwiththepopularizationofdriverfatiguewarningsystem,thecontinuousdevelopmentandimprovementoffatiguedrivingdetectionsystemtechnologyisimminent.Toovercomethelimitationsofasinglesensorinfatiguedetection,wei

2、mprovethefatiguedrivingdetectionratethroughcomprehensiveanalysisthesethreefeaturesofthedriver’seyesandmouthstatus,andthevehicletravelingtrajectories.Firstofall,thispaperobtainthedriver'seyes,mouthandtheroadfeaturedatafromthedriver’sfacialimageandroadimagethroughinstallingcamerasinthecarandthefront

3、ofthecar,usingimageacquisitionprogramoftheinfraredlightauxiliarysourcestoensuretheall-timeavailabilityofthesystemandfilterouttheeffectofnaturallight;extractingtheeyefatiguecharacteristicbytextureanalysisinfrareddetectionmethod,andthendetectandlocatetheeyesandmouthareabytheintelligentADABOOSTalgori

4、thm;wefirstlocatethenose,andthenenhancethemouthdetectionratethroughthegeometricpositionrelationshipofnoseandmouse,thencalculatetheopeningdegreeofthemouthaccordingtotheareathesize;calculatinglaneofroadimageusingasimplelinearlanemodel,andobtaintheparametricofthelinearlanemodelusingthebetterrobustnes

5、sprobabilityHoughtransform,socalculatetheyawrate.Thispaperproposetheeyesclosedtimeratetoanalyzeeyefeature,onthebasisofPERCLOSalgorithm,thismethodlettheratioofthedetectedeyesclosedtimeandnormaleyesclosedtimeasthestandardoffatigueanalysis,forthemouthfatigueCharacteristicAnalysis,weusethedual-thresho

6、ldyawnanalysismethodstoanalyzefatigueanddistinguishnon-yawn;thispaperdetectslanedeviationusingtheyawrate,whichisdefinedastheratiooftheleftandrightlanelinesandtheimagehorizontalaxisangle.Finally,dofusionanalysisusingtheweightedaverage,withselectthePRECLOS,theeyesclosedtime,yawntimeandthelaneyawrate

7、asthefeaturesvalue,experimentshowthattheaccuracyratehasgreatlyimproved.Keywords:AutomobileActivesafety;fatiguedrivingdetection;informationfusion;featureextraction;imageacquisition4万方数据西华大学硕士学位论文目录XihuaUniversity.

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。