| 行人行为的奇异性检测和正常行为分类 |
| |
| 引用本文： | 王威,张鹏,王润生,陈宜稳.行人行为的奇异性检测和正常行为分类[J].计算机工程与应用,2010,46(9):173-176. |
| |
| 作者姓名： | 王威 张鹏 王润生 陈宜稳 |
| |
| 作者单位： | 国防科技大学 ATR实验室，长沙 410073 |
| |
| 摘 要： | 提出了一种固定场景视频序列异常检测和正常行为分类的方法。该方法定义行人正常的走路和跑动为正常行为，最大的特点在于时空联合特征的选择。首先选用区域特征，通过分析正常行为找到特征的在时间上的统计规律，视频序列中行人不符合规律的行为被判定为异常。然后选用具有时空联合分布特点的目标轮廓特征，通过支持向量机（Support Vector Machine，SVM）进行训练，在训练的基础上判断目标行为是走路还是跑动。该方法在一定样本基础上进行了实验，实验结果表明，该方法能够较好进行行为检测和分类，性能比其他方法也有提高。
|
| 关 键 词： | 奇异性检测 行为分类 支持向量机 特征选取 |
| 收稿时间： | 2008-9-18 |
| 修稿时间： | 2008-12-4
|
Behavior abnormality detection and normal behavior classification of Human |
| |
| WANG Wei,ZHANG Peng,WANG Run-sheng,CHEN Yi-wen.Behavior abnormality detection and normal behavior classification of Human[J].Computer Engineering and Applications,2010,46(9):173-176. |
| |
| Authors: | WANG Wei ZHANG Peng WANG Run-sheng CHEN Yi-wen |
| |
| Affiliation: | ATR Lab，National University of Defence Technology，Changsha 410073，China |
| |
| Abstract: | A method is proposed for behavior abnormality detection and normal behavior classification of human in video sequence.In this method,the walk activity and the run activity are defined as normal behaviors,and the main innovative point is the selection of the spatio-temporal characters.Firstly,the region character is selected,so the statistical rule can be acquired by the normal behavior analysis.The behavior which can not accord with the rule is thought of abnormal.Then the outline character is selected too.... |
| |
| Keywords: | abnormality detection behavior classification Support Vector Machine(SVM) character selection |
| 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 |
