基于背景减法的游泳者检测

山东大学学报(工学版)

基于背景减法的游泳者检测

崔英, 陈文楷, 雷飞

北京工业大学电子信息与控制工程学院, 北京 100022

收稿日期:2007-09-27 修回日期:1900-01-01 出版日期:2008-02-16 发布日期:2008-02-16
通讯作者: 崔英

Swimmer detection based on background subtraction

CUI Ying， CHEN Wen-kai， LEI Fei

College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China

Received:2007-09-27 Revised:1900-01-01 Online:2008-02-16 Published:2008-02-16
Contact: CUI Ying

摘要/Abstract

摘要： 针对游泳池监视系列图像中的游泳者进行检测,提出了基于背景减法的游泳者溺水检测方法.该方法通过架设在泳池内的固定摄像机获得连续视频监视图像,采用独立混合高斯模型描述每一被观察的像素,建立自适应背景模型并实时更新.前景目标检出后,对所得前景图像进行阴影检测和噪音去除,使得检测结果更加理想,为目标分类打好基础.实验结果表明,该方法能准确的检测出游泳者并有效的去除阴影部分.

关键词: 背景减法, 高斯混合模型, 游泳者检测, 视频监测

Abstract: Swimmer detection for visual surveillance of a pool was studied. A fixed camera installed on the pool wall can obtain a consecutive sequence of visual surveillance. A Gaussian mixed model was used to describe each pixel, and a selfadapted background model was set up, which can be updated. The shadows and noises must be removed to obtain better results after the foreground objects are separated. The experimental results show that this method is effective in detecting swimmers and eliminating shadows.

Key words: background subtraction, Gaussian mixture model, swimmer detection, visual surveillance

中图分类号:

TP391

崔英,陈文楷,雷飞 . 基于背景减法的游泳者检测[J]. 山东大学学报(工学版), 2008, 38(1): 39-42 .

CUI Ying,CHEN Wen-kai,LEI Fei . Swimmer detection based on background subtraction[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2008, 38(1): 39-42 .

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	张杨,陈飞,徐海平. 基于图像块先验的低秩近似和维纳滤波的去噪算法[J]. 山东大学学报(工学版), 2017, 47(3): 16-20.
[2]	梁浩哲,徐树奎,李国辉,张军. 面向监控视频的行为模式挖掘[J]. 山东大学学报(工学版), 2011, 41(6): 24-30.
[3]	陈涛,方志刚,徐洁 . 基于人脸和语音的混合型身份认证系统[J]. 山东大学学报(工学版), 2008, 38(2): 56-60 .