首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于光流的人体运动实时检测方法
引用本文:施家栋,王建中,王红茹.基于光流的人体运动实时检测方法[J].北京理工大学学报,2008,28(9):794-797.
作者姓名:施家栋  王建中  王红茹
作者单位:北京理工大学,爆炸科学与技术国家重点实验室,北京,100081
摘    要:针对目前广泛使用的光流法计算耗时严重问题,提出了基于差分图像绝对值和(SAD)与光流法相结合的人体运动检测方法. 通过计算SAD检测出运动区域,在已确定的运动区域内进行Horn-Schunck光流场计算,准确地计算出人体的运动信息. 在后续处理中,应用形态学的闭运算和连通性分析,较完整地分割出人体运动目标. 实验结果表明,该方法有效地提高了系统的计算速度,能够实时准确地对人体运动进行检测.

关 键 词:人体运动  差分图像绝对值(SAD)  光流法  目标分割
收稿时间:2008/4/17 0:00:00

Real-Time Detection Method of Human Motion Based on Optical Flow
SHI Jia-dong,WANG Jian-zhong and WANG Hong-ru.Real-Time Detection Method of Human Motion Based on Optical Flow[J].Journal of Beijing Institute of Technology(Natural Science Edition),2008,28(9):794-797.
Authors:SHI Jia-dong  WANG Jian-zhong and WANG Hong-ru
Institution:State Key Laboratory of Explosion Science and Technology, Beijing Institute of Technology, Beijing 100081, China;State Key Laboratory of Explosion Science and Technology, Beijing Institute of Technology, Beijing 100081, China;State Key Laboratory of Explosion Science and Technology, Beijing Institute of Technology, Beijing 100081, China
Abstract:Considering the problem that the traditional optical flow algorithm is a time-consuming computation.An integrated method of detecting human motion is proposed based on the sum of absolute differences(SAD) and optical flow.The motion sub-region is detected by the computation of SAD.The optical flow vectors of the object can be obtained by computing optical flow on the motion sub-region.In the post processing,closing and connected components analysis are used for the segmentation of human object.Experimental results showed the effectiveness and robustness of the proposed method.
Keywords:human motion  sum of absolute differences(SAD)  optical flow method  object segmentation
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《北京理工大学学报》浏览原始摘要信息
点击此处可从《北京理工大学学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号