中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
机构
采集方式
内容类型
发表日期
学科主题
筛选

浏览/检索结果: 共5条,第1-5条 帮助

条数/页: 排序方式:
Exploring Local and Overall Ordinal Information for Robust Feature Description 期刊论文  OAI收割
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 卷号: 38, 期号: 11, 页码: 2198-2211
作者:  
Zhenhua Wang;  Bin Fan;  Gang Wang;  Fuchao Wu
  |  收藏  |  浏览/下载:40/0  |  提交时间:2018/01/03
鲁棒的局部图像特征匹配方法 学位论文  OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院大学, 2014
作者:  
王振华
收藏  |  浏览/下载:60/0  |  提交时间:2015/09/02
图像特征匹配研究 学位论文  OAI收割
工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2011
作者:  
樊彬
收藏  |  浏览/下载:43/0  |  提交时间:2015/09/02
Color transfer and Retinex theory based illumination invariance 会议论文  OAI收割
International Conference on Information Computing and Automation, Hefei, China, December 20-22, 2007
作者:  
Sun J(孙静);  Tang YD(唐延东)
收藏  |  浏览/下载:20/0  |  提交时间:2012/06/06
Target track system design based on circular projection (EI CONFERENCE) 会议论文  OAI收割
ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China
Song H.-J.; Zhu M.; Hu S.; Shen M.-L.
收藏  |  浏览/下载:22/0  |  提交时间:2013/03/25
Template matching is the process of searching the present and the location of a reference image or an object in a scene image. Template matching is a classical problem in a scene analysis: given a reference image of an object  decide whether that object exists in a scene image under analysis  and find its location if it does. The template matching process involves cross-correlating the template with the scene image and computing a measure of similarity between them to determine the displacement. The conventional matching method used the spatial cross-correlation process which is computationally expensive. Some algorithms are proposed for this speed problem  such as pyramid algorithm  but it still can't reach the real-time for bigger model image. Moreover  the cross-correlation algorithm can't be effective when the object in the image is rotated. Therefore  the conventional algorithms can't be used for practical purpose. In this paper  an algorithm for a rotation invariant template matching method based on different value circular projection target tracking algorithm is proposed. This algorithm projects the model image as circular and gets the radius and the sum of the same radius pixel value. The sum of the same radius pixel value is invariable for the same image and the any rotated angle image. Therefore  this algorithm has the rotation invariant property. In order to improve the matching speed and get the illumination invariance  the different value method is combined with circular projection algorithm. This method computes the different value between model image radius pixel sum and the scene image radius pixel sum so that it gets the matching result. The pyramid algorithm also is been applied in order to improve the matching speed. The high speed hardware system also is been design in order to meet the real time requirement of target tracking system. The results show that this system has the good rotate invariance and real-time property.