| 监控视频中正面人脸快速判别方法 |
| |
| 引用本文： | 杨建,徐玮,袁晶,刘煜,张茂军.监控视频中正面人脸快速判别方法[J].计算机工程与应用,2014,50(20):176-181. |
| |
| 作者姓名： | 杨建 徐玮 袁晶 刘煜 张茂军 |
| |
| 作者单位： | 国防科学技术大学 信息系统与管理学院，长沙 410073 |
| |
| 基金项目： | 国家自然科学基金(No.61175006)；北京市自然科学基金(No.4132080)。 |
| |
| 摘 要： | 视频监控领域由于其数据量巨大使得对视频分析变得更加困难，找到视频中正面人脸图片能够使得分析变得简单。正面人脸判别采用了基于积分通道特征和Adaboost的方法，通过提取积分通道特征，利用Adaboost训练分类器，对人脸检测窗口进行正面人脸快速判别。实验结果表明，该方法具有比较好的判别速度和精度，能够应用于大部分监控视频。
|
| 关 键 词： | 监控视频 视频分析 积分通道特征 Adaboost |
Method for rapid discriminant of positive face in surveillance video |
| |
| YANG Jian,XU Wei,YUAN Jing,LIU Yu,ZHANG Maojun.Method for rapid discriminant of positive face in surveillance video[J].Computer Engineering and Applications,2014,50(20):176-181. |
| |
| Authors: | YANG Jian XU Wei YUAN Jing LIU Yu ZHANG Maojun |
| |
| Affiliation: | College of Information System and Management, National University of Defense Technology, Changsha 410073, China |
| |
| Abstract: | A problem has occured when the video analysis work is done because of the big data of the surveillance video, it is convenient to analyze the video if the positive face has found. Discriminant of the positive face uses the method based on integral channel features and Adaboost, in the training section, the Adaboost uses the extracted integral channel fea-tures to train the classifier, which is used to the rapid discriminant of the positive face of the face detection window. Experi-mental results show that this method can meet most surveillance video with good computing speed and accuracy. |
| |
| Keywords: | surveillance video video analysis integral channel features Adaboost |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
