您的位置:首页  > 论文页面

基于像素法和纹理分析方法的人群密度融合判别方法研究

发表时间:2014-02-28  浏览量:15554  下载量:7589
全部作者: 邓琳,刘英豪,贾配洋,张雪波
作者单位: 南开大学计算机与控制工程学院
摘 要: 针对监控视频中的中、低密度人群,采用基于像素的方法对人群进行图像分析以得到前景图像的总像素数和边缘图像的总像素数。针对监控视频中的高密度人群,采用纹理分析方法,从统计角度,利用灰度共生矩阵提取出纹理特征,并进行归一化。再利用融合判别方法,根据前景像素占整个背景像素的比例将当前帧图像判定为中、低密度或高密度;利用中、低密度情况下前景图像的总像素数和边缘图像的总像素数与人群密度存在正相关的关系及高密度情况下纹理特征与人群密度之间的线性相关性,采用最小二乘曲线拟合的方法分别得到中、低密度及高密度下的人群密度曲线,实现了具有较高准确度的针对不同密度的人群数目估计。
关 键 词: 信息科学与系统科学基础学科;视频监控;人群密度估计;像素法;灰度共生矩阵;最小二乘拟合
Title: Fusion identification method based on pixels and texture analysis of crowd density
Author: DENG Lin, LIU Yinghao, JIA Peiyang, ZHANG Xuebo
Organization: College of Computer and Control Engineering, Nankai University
Abstract: In view of the surveillance video of the middle and low density of population, the method based on pixels for people was used to get the foreground image after image analysis of the total image pixels and edge pixels. For high density crowd in surveillance video, we adopted the method of texture analysis from the perspective of statistics, and extracted the texture features based on the gray level co-occurrence matrix, then normalized the results. Then, we used the assessment method of fusion to determine low or high density based on foreground pixel proportion in the whole background pixels of the current frame image. Finally, because of the positive correlation among the foreground image pixels, edge pixels and population density, and the linear correlation between texture features and population density, we used the method of least squares respectively to get the crowd density curves in middle, low and high density of population, and realized the estimation for different population density with higher accuracy.
Key words: basic subject of information science and system science; crowd monitoring; crowd density estimating; pixel method; gray level co-occurrence matrix; the least squares method
发表期数: 2014年2月第4期
引用格式: 邓琳,刘英豪,贾配洋,等. 基于像素法和纹理分析方法的人群密度融合判别方法研究[J]. 中国科技论文在线精品论文,2014,7(4):383-390.
 
0 评论数 0
暂无评论
友情链接