基于视频图像处理的人数统计方法  

Person Number Counting Based on Video Image Processing

作　　者：闫敬文[1] 樊秋月[1] 

机构地区：[1]汕头大学电子工程系,广东汕头515063

出　　处：《汕头大学学报（自然科学版）》2008年第2期69-73,共5页Journal of Shantou University：Natural Science Edition

摘　　要：以数学形态学滤波为基础,提出一种基于视频图像处理的人数统计方法.该方法利用图像灰度值并设置适当的像素阈值以判断头部区域,对出现在之前两帧中的人进行累加计数,并设置标志位,通过相邻两帧差减判断静止的人,同时也设置静止标志位.实验结果表明,该方法能较准确地完成人数的统计.With morphologic filtering, a person number counting method is proposed for video image processing. The hair region is extracted by using the gray value, and the proper threshold of pixel value is set to estimate the real head region. An adaptive threshold is used and symbol bits are set in the number counting process. Static symbol bits for the static ones are set and judged by subtraction of consecutive two frames. It is shown in experiments that the person number counting method is accurate.

关 键 词：视频图像处理 人数统计 数学形态学滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]