求助文献What image information is important in silhouette导出-based gait recognition?

来源：蜘蛛抓取(WebSpider) 时间：2017-12-08 08:03 标签： silhouette眼镜上海
Human Recognition Based on Gait Energy Image and Invariant Moments--《Computer & Digital Engineering》2009年10期
Human Recognition Based on Gait Energy Image and Invariant Moments
Wang Liqiao Pei Yanan(Modern Education Technology and Information Center,Henan University of Science and Technology,Luoyang 471003)
In this paper,a new gait energy image and invariant moments based gait recognition algorithm is presented.Gait energy image shape,as a static appearance feature also contains useful information for identification,and the paper testify that gait energy image is less sensitive to silhouette noise.Secondly,the basic theory of moment invariants and seven moment invariants which were proposed by Hu are introduced.Using the traits of invariant moments,such as shift,rotation and scale invariant,invariant moment is extracted from the original gait energy image as input features,and the invariant moments least-distance classifier is adopted to recognize subjects.Finally we compare the proposed based on gait energy image and invariant moments gait recognition approach with other new gait recognition approaches on CASIA Gait Database.Experimental results show that the proposed approach is valid and has encouraging recognition performance.
【CateGory Index】：
supports all the CNKI
only supports the PDF format.
Similar Journals
(C)2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reservedIncremental Learning for Video-Based Gait Recognition With LBP Flow. - Abstract - Europe PMC
Europe PMC requires Javascript to function effectively.
Either your web browser doesn't support Javascript or it is currently turned off. In the latter case, please
turn on Javascript support in your web browser and reload this page.
https://orcid.org
Search worldwide, life-sciences literature
Yunhong Wang
Zhaoxiang Zhang
James J Little
[05 Jun ):77-89]
Research Support, Non-U.S. Gov't, Journal Article
Gait analysis provides a feasible approach for identification in intelligent video surveillance. However, the effectiveness of the dominant silhouette-based approaches is overly dependent upon background subtraction. In this paper, we propose a novel incremental framework based on optical flow, including dynamics learning, pattern retrieval, and recognition. It can greatly improve the usability of gait traits in video surveillance applications. Local binary pattern (LBP) is employed to describe the texture information of optical flow. This representation is called LBP flow, which performs well as a static representation of gait movement. Dynamics within and among gait stances becomes the key consideration for multiframe detection and tracking, which is quite different from existing approaches. To simulate the natural way of knowledge acquisition, an individual hidden Markov model (HMM) representing the gait dynamics of a single subject incrementally evolves from a population model that reflects the average motion process of human gait. It is beneficial for both tracking and recognition and makes the training process of the HMM more robust to noise. Extensive experiments on widely adopted databases have been carried out to show that our proposed approach achieves excellent performance.
)- subscription required
Show all items
Show all items
Show all items
Show all items
CitePeer Related Articles
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items
Show all items

我要回帖

更多关于 silhouette眼镜上海 的文章

 

随机推荐