globalchange  > 气候变化与战略
CSCD记录号: CSCD:5732667
论文题名:
双人交互行为的稀疏表征方法
其他题名: Sparse Representation Method for Human Interaction
作者: 陈昌红; 张杰; 刘峰
刊名: 模式识别与人工智能
ISSN: 1003-6059
出版年: 2016
卷: 29, 期:5, 页码:2254-2259
语种: 中文
中文关键词: 交互行为识别 ; 特征融合 ; 稀疏表征
英文关键词: Human Interaction Recognition ; Feature Fusion ; Sparse Representation
WOS学科分类: COMPUTER SCIENCE INTERDISCIPLINARY APPLICATIONS
WOS研究方向: Computer Science
中文摘要: 提出一种双人交互行为的稀疏表征方法,融合体现全局变化的轨迹特征和突出区域运动的时空特征.首先,采用词袋模型得到轨迹特征的稀疏表示.然后,对提取的时空特征采用三层时空金字塔分解得到多层特征,并对其进行稀疏编码,利用多尺度Maxpooling算法融合得到局部稀疏特征.最后,将2种稀疏特征加权串联得到双人交互行为的稀疏表征.采用基于隐动态条件随机场的识别算法对文中提取的稀疏表征进行验证,通过实验证明其有效性.
英文摘要: In this paper, a sparse representation method for human interaction is proposed. The trajectory feature embodying global changes is fused with spatio-temporal feature emphasizing local movement. Firstly, the sparse representation of the trajectory feature is obtained by the bag of words model. Then, multi-level spatio-temporal features are produced by three layered spatial-temporal pyramid and processed by sparse coding. Multi-scale maxpooling algorithm is employed to obtain the local sparse feature. Finally, two kinds of sparse features are weighted and connected to obtain the sparse representation of human interaction. The dynamic latent conditional random field model is employed to verify the proposed sparse representation and the experimental results demonstrate the effectiveness.
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/151104
Appears in Collections:气候变化与战略

Files in This Item:

There are no files associated with this item.


作者单位: 南京邮电大学, 江苏省图像处理与图像通信重点实验室, 南京, 江苏 210003, 中国

Recommended Citation:
陈昌红,张杰,刘峰. 双人交互行为的稀疏表征方法[J]. 模式识别与人工智能,2016-01-01,29(5):2254-2259
Service
Recommend this item
Sava as my favorate item
Show this item's statistics
Export Endnote File
Google Scholar
Similar articles in Google Scholar
[陈昌红]'s Articles
[张杰]'s Articles
[刘峰]'s Articles
百度学术
Similar articles in Baidu Scholar
[陈昌红]'s Articles
[张杰]'s Articles
[刘峰]'s Articles
CSDL cross search
Similar articles in CSDL Cross Search
[陈昌红]‘s Articles
[张杰]‘s Articles
[刘峰]‘s Articles
Related Copyright Policies
Null
收藏/分享
所有评论 (0)
暂无评论
 

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