A novel approach for crowd video monitoring of subway platforms (1).pdf

A novel approach for crowd video monitoring of subway platforms (1).pdf

ID:34114652

大小:961.04 KB

页数:6页

时间:2019-03-03

A novel approach for crowd video monitoring of subway platforms (1).pdf_第1页
A novel approach for crowd video monitoring of subway platforms (1).pdf_第2页
A novel approach for crowd video monitoring of subway platforms (1).pdf_第3页
A novel approach for crowd video monitoring of subway platforms (1).pdf_第4页
A novel approach for crowd video monitoring of subway platforms (1).pdf_第5页
资源描述:

《A novel approach for crowd video monitoring of subway platforms (1).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、Optik124(2013)5301–5306ContentslistsavailableatScienceDirectOptikjournalhomepage:www.elsevier.de/ijleoAnovelapproachforcrowdvideomonitoringofsubwayplatformsXuemina,∗bbbHu,HongZheng,WenweiWang,XiLiaSchoolofPhysicsandElectronics,HubeiUniversity,368Youy

2、iAvenue,Wuhan,Hubei430062,ChinabLabforImageProcessingandIntelligentSystems,SchoolofElectronicInformation,WuhanUniversity,129LuoyunRoad,Wuhan,Hubei430072,ChinaarticleinfoabstractArticlehistory:Crowdmonitoringinadensecrowdscenehasbecomeanimportantandch

3、allengingtopicinthefieldofReceived16October2012videosurveillancesystem.ThispaperproposesanovelcrowdmonitoringapproachforsubwayplatformsAccepted18March2013toaddressrequirementsinrailtrafficmanagement.Firstly,animprovementforMixtureGaussianback-groundmod

4、elingispresentedtosegmentthecrowd.Intheprocessoffeatureextraction,theconceptoftheweightedareaisproposedtosolvetheproblemoftheperspectiveofimages.TodealwiththeissueKeywords:oftheocclusionbetweenindividuals,animprovedgradientfeatureisdevelopedinthispap

5、er.Andthen,SubwayplatformAdaptiveBoostclassifierwiththefeatureweightedareaandtheimprovedgradientisusedtoestimateWeightedareathegradientcrowddensity.Finally,thecrowdiscountedbythemethodoflinearregression.TheexperimentalImprovedresultsshowthatthepropose

6、dapproachisfeasibleandeffectiveforcrowdmonitoringinrealsubwayDensityestimationplatforms.Crowdcounting©2013ElsevierGmbH.Allrightsreserved.1.Introductionispoorforanexcessivelydensecrowdbecauseoftheocclusionbetweenindividuals.Withtheaccelerationofurbani

7、zation,moreandmorepeoplegoAnotherisbasedonastatisticalgorithmwithglobalorlocaltocitiesforlivelihood,placingtremendouspressureonthecities’features,suchastextures,gradient,area,edgefeaturepoints.Chowinfrastructures.Denselycrowdedplaces,suchassubwaystat

8、ions,andChow[7],Maranaetal.[8]andWuetal.[9]didsomeresearchesareusuallyverycongested,whichhaveanegativeeffectonthepeo-incrowddensityestimation.Ryanetal.[10]andChanetal.[11]pro-pleontheway.Moreover,disastersarepronetohappeninginsuchposedacrowdcountinga

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。