首页 | 本学科首页   官方微博 | 高级检索  
     

新的时空特征点检测方法
引用本文:尹建芹,王晶晶,李金屏.新的时空特征点检测方法[J].吉林大学学报(工学版),2012,42(3):754-758.
作者姓名:尹建芹  王晶晶  李金屏
作者单位:1. 济南大学山东省网络环境智能计算技术重点实验室,济南,250022
2. 山东师范大学物理与电子科学学院,济南,250014
基金项目:山东省高等学校发展计划项目,济南市高等学校科研计划项目
摘    要:提出了基于累积差熵的时空特征点检测算法。首先利用周期性时空检测方法检测视频的关键特征点;然后提出了视频累积差熵的概念,用累积差熵作为特征点的评价准则;以该准则为基础,选择具有累积差熵大的特征点作为关键点,并对关键视频进行聚类,得到关键视频的原型特征。实验结果表明:本文方法可以简单有效地去除非运动信息得到的关键点,可以较好地用于动作识别、表情识别等视频分析领域。

关 键 词:信息处理技术  时空特征点    视频分析  动作识别

New space-time interest point detection scheme based on cumulative entropy difference
YIN Jian-qin,WANG Jing-jing,LI Jin-ping.New space-time interest point detection scheme based on cumulative entropy difference[J].Journal of Jilin University:Eng and Technol Ed,2012,42(3):754-758.
Authors:YIN Jian-qin  WANG Jing-jing  LI Jin-ping
Affiliation:1(1.Shandong Provincial Key Laboratory of Network Based Intelligent Computing,University of Jinan,Jinan 250022,China;2.College of Physics and Electronics,Shandong Normal University,Jinan 250014,China)
Abstract:A new scheme to detect space-time interest points based on cumulative entropy difference is proposed for human action recognition and video analysis.First,periodic space-time features are detected.Second,the concept of cumulative entropy difference is put forward as the criterion to evaluate the interest points.Third,the points with high cumulative entropy are selected as the final key points.Finally,c-means cluster analysis is applied to find the features,and the prototype of the key video is obtained.The video is converted to the feature vector presented by the prototype;then the video classification is conducted.Experimental results show that the cumulative entropy difference evaluation can effectively remove the noise cuboids,and the method based on the evaluation can realize human action analysis and facial expression recognition.
Keywords:information processing  space-time interest points  entropy  action recognition  video analysis
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号