NSSC OpenIR  > 空间技术部
基于姿态时空特征的人体行为识别方法
Alternative TitleHuman Action Recognition Based on Pose Spatio-Temporal Features
郑潇; 彭晓东; 王嘉璇
Department空间技术部
Source Publication计算机辅助设计与图形学学报
Volume30Issue:9Pages:1615-1624
ISSN1003-9775
Language中文
Keyword行为识别 姿态时空特征 Fisher向量 加权融合
Abstract为了高效、准确地获取视频中的人体行为和运动信息,提出一种基于人体姿态的时空特征的行为识别方法.首先在获取视频中各帧图像的人体关节位置的基础上,提取关节信息描述姿态变化,具体包括在空间维度上提取每帧图像的关节位置关系、时间维度上计算关节空间关系的变化,二者共同构成姿态时空特征描述子;然后利用Fisher向量模型对不同类型的特征描述子分别进行编码,得到固定维度的Fisher向量;最后对不同类型的Fisher向量加权融合后进行分类.实验结果表明,该方法能够有效地识别视频中的人体复杂动作行为,提高行为识别率.
Other AbstractIn order to extract human motion information efficiently and improve the accuracy of action recognition from videos, an approach for action recognition based on human pose spatio-temporal features is proposed. Firstly, with the joint positions of human body in each frame of the video acquired, we extracted pose information by handcrafted features. Specifically, the positions of joints and relatives in the spatial dimension, as well as the change of that in the temporal dimension were calculated. The two together constituted human pose spatiotemporal feature descriptors. Then the Fisher Vector model was utilized to compute fixed dimension Fisher vector for each descriptor separately. Lastly, features were weighted to fusion for classification. Experimental results show that the proposed algorithm can effectively improve action recognition performance.
Indexed ByCSCD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/6599
Collection空间技术部
Recommended Citation
GB/T 7714
郑潇,彭晓东,王嘉璇. 基于姿态时空特征的人体行为识别方法[J]. 计算机辅助设计与图形学学报,30(9):1615-1624.
APA 郑潇,彭晓东,&王嘉璇.
MLA 郑潇,et al."基于姿态时空特征的人体行为识别方法".计算机辅助设计与图形学学报 30.9
Files in This Item:
File Name/Size DocType Version Access License
20183091615-1624.pdf(1203KB)期刊论文出版稿开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[郑潇]'s Articles
[彭晓东]'s Articles
[王嘉璇]'s Articles
Baidu academic
Similar articles in Baidu academic
[郑潇]'s Articles
[彭晓东]'s Articles
[王嘉璇]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[郑潇]'s Articles
[彭晓东]'s Articles
[王嘉璇]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.