CASIA OpenIR  > 智能感知与计算研究中心
View-invariant Action Recognition Using Cross Ratios Across Frames
Yeyin Zhang; Kaiqi Huang; Yongzhen Huang; Tieniu Tan
2009
会议名称International Conference on Image Processing
会议录名称IEEE International Conference on Image Processing, 2009
页码3549--3552
会议日期2009
会议地点Cairo, Egypt
摘要We present a new method of computing invariants in videos captured from different views to achieve view-invariant action recognition. To avoid the constraints of collinearity or coplanarity of image points for constructing invariants, we consider several neighboring frames to compute cross ratios, namely cross ratios across frames (CRAF), as our invariant representation of action. For every five points sampled with different intervals from the trajectories of action, we construct a pair of cross ratios (CRs). Afterwards, we transform the CRs to histograms as the feature vectors for classification. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in effectiveness and stability.
关键词Computational Geometry   gesture Recognition   image Classification 
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12707
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Yeyin Zhang,Kaiqi Huang,Yongzhen Huang,et al. View-invariant Action Recognition Using Cross Ratios Across Frames[C],2009:3549--3552.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yeyin Zhang]的文章
[Kaiqi Huang]的文章
[Yongzhen Huang]的文章
百度学术
百度学术中相似的文章
[Yeyin Zhang]的文章
[Kaiqi Huang]的文章
[Yongzhen Huang]的文章
必应学术
必应学术中相似的文章
[Yeyin Zhang]的文章
[Kaiqi Huang]的文章
[Yongzhen Huang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。