计算机技术与发展Issue(2)：101-104,109,5.DOI:10.3969/j.issn.1673-629X.2016.02.023
基于帧间特征和连通域检测的人数统计
People Counting Based on Inter-frame Features and Connected Domain Detection
摘要
Abstract
In order to manage airports,railway stations and bus stations and other crowded places fixed with a better way,a simple and ef-ficient personnel traffic statistics algorithm was proposed. First,the video images was converted into grayscale images,and then the fore-ground image was extracted using the frame difference method and was converted into binary image. Second,connected domain was de-tected based on matching between the points of up-contour and down-contour,and then head features were extracted using shape and gray information of head. Finally,people was counted by tracking head connected domain. In this head tracking and counting algorithm presented,use the basic information and container of head connected domain in the video image for tracking and counting. Experimental results show that the algorithm has a good head tracking and counting results.关键词
人头特征/跟踪/计数/连通域Key words
head features/tracking/counting/connected domain分类
信息技术与安全科学引用本文复制引用
朱家新,郭德全,兰时勇..基于帧间特征和连通域检测的人数统计[J].计算机技术与发展,2016,(2):101-104,109,5.基金项目
国家“863”高技术发展计划项目(2013AA013802) （2013AA013802）
