Large Scale Crowd Analysis Based on Convolutional Neural Network

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Large Scale Crowd Analysis Based on Convolutional Neural Network
	Lijun, Cao; Kaiqi, Huang
刊名	Pattern Recognition
	2015-06-06
卷号	48 期号:10 页码:3016–3024
关键词	Crowd Analysis Flow Counting Cnn Large Scaledata
英文摘要	Nowadayscrowdsurveillanceisanactiveareaofresearch.Crowdsurveillanceisalwaysaffectedby variousconditions,suchasdifferentscenes,weather,ordensityofcrowd,whichrestrictsthereal application. Thispaperproposesaconvolutionalneuralnetwork(CNN)basedmethodtomonitorthe number ofcrowd flow,suchasthenumberofenteringorleavingpeopleinhighdensitycrowd.Itusesan indirect strategyofcombiningclassification CNNwithregressionCNN,whichismorerobustthanthe direct way.Alargeenoughdatabaseisbuiltwithlotsofrealvideosofpublicgates,andplentyof experimentsshowthattheproposedmethodperformswellundervariousweatherconditionsnomatter either indaytimeoratnight.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/11816]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Kaiqi, Huang
作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Lijun, Cao,Kaiqi, Huang. Large Scale Crowd Analysis Based on Convolutional Neural Network[J]. Pattern Recognition,2015,48(10):3016–3024.
APA	Lijun, Cao,&Kaiqi, Huang.(2015).Large Scale Crowd Analysis Based on Convolutional Neural Network.Pattern Recognition,48(10),3016–3024.
MLA	Lijun, Cao,et al."Large Scale Crowd Analysis Based on Convolutional Neural Network".Pattern Recognition 48.10(2015):3016–3024.