| 复杂背景下人体检测算法 |
| |
| 引用本文： | 孙宏国,李天然,蒲宝明,张全发,王慧静.复杂背景下人体检测算法[J].计算机系统应用,2013,22(4):134-137,120. |
| |
| 作者姓名： | 孙宏国 李天然 蒲宝明 张全发 王慧静 |
| |
| 作者单位： | 中国科学院 研究生院, 北京 100049
;中国科学院 沈阳计算技术研究所, 沈阳 110168;南京师范大学 地理科学学院, 南京 210023;中国科学院 沈阳计算技术研究所, 沈阳 110168;中国科学院 研究生院, 北京 100049
;中国科学院 沈阳计算技术研究所, 沈阳 110168;中国科学院 研究生院, 北京 100049
;中国科学院 沈阳计算技术研究所, 沈阳 110168 |
| |
| 摘 要： | 静态图像的人体识别技术在实际视频监控场景中, 面临背景复杂、图像分辨率低、光照影响和噪声干扰等问题, 这些多变性以及可能发生的遮挡给单一图像中的人体识别技术提出了挑战. 设计和实现一种复杂背景下的人体检测算法, 基于HOG人体检测算法, 使用积分直方图计算HOG特征, 并用级联SVM分类器对样本进行训练. 实验结果表明, 该算法在复杂视频监控场景中进行人体检测比其它人体检测算法具有更高的准确率和更快的检测速度.
|
| 关 键 词： | 视频监控 人体检测 HOG SVM |
| 收稿时间： | 2012/9/26 0:00:00 |
| 修稿时间： | 2012/11/18 0:00:00 |
Human Detection Algorithm in Complex Background |
| |
| SUN Hong-Guo,LI Tian-Ran,PU Bao-Ming,ZHANG Quan-Fa and WANG Hui-Jing.Human Detection Algorithm in Complex Background[J].Computer Systems& Applications,2013,22(4):134-137,120. |
| |
| Authors: | SUN Hong-Guo LI Tian-Ran PU Bao-Ming ZHANG Quan-Fa and WANG Hui-Jing |
| |
| Affiliation: | Graduate University, Chinese Academy of Sciences, Beijing 100049, China
;Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, China;Nanjing Nornal University, College of Geographical Science, Nanjing 210023, China;Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, China;Graduate University, Chinese Academy of Sciences, Beijing 100049, China
;Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, China;Graduate University, Chinese Academy of Sciences, Beijing 100049, China
;Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, China |
| |
| Abstract: | Human detection under static background may be not suitable to video surveillance which is of complex background, low resolution, small target and noise jamming. All these polytropes and possible occlusion that pose new challenges for us to recognize human after motion detection in single image. For this reason, this article design and implement an human detection algorithm using integral histogram instead of HOG under complex background based on HOG human detection algorithm. Then the cascade SVM is adopted in my experiment to train the sample. Experiment showed that the algorithm has higher precision and faster speed than other algorithm under video surveillance with complex background. |
| |
| Keywords: | video surveillance human detection HOG SVM |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
