ISCAS OpenIR
基于局部先验模型的单目视频人体运动跟踪
Alternative Titlemonocular tracking of human motion with local prior models
王文中; 王兆其; 邓小明; 夏时洪; 邱显杰
2011
Source计算机辅助设计与图形学学报
ISSN1003-9775
Volume23Issue:9Pages:1545-1552
English Abstract在基于模型的单目视频人体运动跟踪中,视频图像信息往往不足以恢复人体姿态,通常需要加入对姿态的先验约束才能得到合理的解.为了有效地刻画人体运动过程的时变动态特征,提出局部先验模型,其中包括局部动态过程和局部姿态分布密度,通过在样本空间中检索出相似姿态的集合,并利用该集合学习模型参数来比较精确地刻画人体的运动规律.实验结果表明,与全局动态模型相比,局部先验模型有效地克服了肢体自遮挡和肢体混淆等问题,取得了更好的跟踪结果.
Indexed TypeCNKI ; EI ; WANFANG
AbstractA novel approach to modelling the dynamics of human motion is presented. The proposed method utilizes locally learnt prior models to encode the time-varying characteristics of human motion. The local priors consist of the probability density of poses and dynamical process of motions. For each input image, the proposed method automatically learns the parameters of these models from a set of training examples that closely match with the query. The experimental results showed that the proposed method outperforms those with global motion models.
Keyword局部先验模型 变形模板 运动跟踪
Department中国科学院计算技术研究所前瞻研究实验室;中国科学院研究生院;中国科学院软件研究所人机交互技术与智能信息处理实验室;
Sponsorship国家自然科学基金(61005039)|国家科技支撑计划(2008BAI50B07)|中国科学院科技助残行动计划(KGCX2-YW-610),中国科学院自动化研究所模式识别国家重点实验室开放课题(20090096)
Language中文
Content Type期刊论文
URIhttp://ir.iscas.ac.cn/handle/311060/16041
Collection中国科学院软件研究所
Recommended Citation
GB/T 7714
王文中,王兆其,邓小明,等. 基于局部先验模型的单目视频人体运动跟踪[J]. 计算机辅助设计与图形学学报,2011,23(9):1545-1552.
APA 王文中,王兆其,邓小明,夏时洪,&邱显杰.(2011).基于局部先验模型的单目视频人体运动跟踪.计算机辅助设计与图形学学报,23(9),1545-1552.
MLA 王文中,et al."基于局部先验模型的单目视频人体运动跟踪".计算机辅助设计与图形学学报 23.9(2011):1545-1552.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王文中]'s Articles
[王兆其]'s Articles
[邓小明]'s Articles
Baidu academic
Similar articles in Baidu academic
[王文中]'s Articles
[王兆其]'s Articles
[邓小明]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王文中]'s Articles
[王兆其]'s Articles
[邓小明]'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.