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12条,第1-10条 帮助

条数/页: 排序方式:
AMI-Net: Convolution Neural Networks With Affine Moment Invariants 期刊论文  OAI收割
IEEE SIGNAL PROCESSING LETTERS, 2018, 卷号: 25, 期号: 7, 页码: 1064-1068
作者:  
Hao, You;  Li, Qi;  Mo, Hanlin;  Zhang, He;  Li, Hua
  |  收藏  |  浏览/下载:26/0  |  提交时间:2019/12/10
图像匹配方法及其在检索中的应用 学位论文  OAI收割
工学硕士, 中国科学院自动化研究所: 中国科学院大学, 2014
陈文龙
收藏  |  浏览/下载:55/0  |  提交时间:2015/09/02
Grassmann manifold based shape matching and retrieval under partial occlusions 会议论文  OAI收割
International Symposium on Optoelectronic Technology and Application 2014, Beijing, China, May 13-15, 2014
作者:  
Li CX(李晨曦);  Shi ZL(史泽林);  Liu YP(刘云鹏);  Xu BS(徐保树)
收藏  |  浏览/下载:27/0  |  提交时间:2014/12/29
An improved multi-scale autoconvolution transform 会议论文  OAI收割
Beijing, China, May 13-15, 2014
作者:  
Shao CY(邵春艳);  Ding QH(丁庆海);  Luo HB(罗海波)
  |  收藏  |  浏览/下载:11/0  |  提交时间:2014/12/29
基于参数化求和不变量与特征重整的形状匹配 期刊论文  OAI收割
中国图象图形学报, 2010, 卷号: 15, 期号: 1, 页码: 122-128
吕玉增; 彭启民; 黎湘
  |  收藏  |  浏览/下载:26/0  |  提交时间:2011/05/23
图像特征检测及应用 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, 2009
作者:  
戴志军
收藏  |  浏览/下载:64/0  |  提交时间:2015/09/02
Symmetry reductions and exact solutions of the affine heat equation 期刊论文  OAI收割
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2008, 卷号: 346, 页码: 521-530
作者:  
Qu, Changzheng;  Huang, Qing
  |  收藏  |  浏览/下载:23/0  |  提交时间:2018/05/31
Pose determination and plane measurement using a trapezium 期刊论文  OAI收割
PATTERN RECOGNITION LETTERS, 2008, 卷号: 29, 期号: 3, 页码: 223-231
作者:  
Duan, Fuqing;  Wu, Fuchao;  Hu, Zhanyi
收藏  |  浏览/下载:87/0  |  提交时间:2015/11/08
Mean shift tracking combining SIFT (EI CONFERENCE) 会议论文  OAI收割
2008 9th International Conference on Signal Processing, ICSP 2008, October 26, 2008 - October 29, 2008, Beijing, China
作者:  
收藏  |  浏览/下载:63/0  |  提交时间:2013/03/25
A novel visual tracking algorithm to cope with occlusion and scale variation is proposed. This method combines mean shift and SIFT algorithm to track object. SIFT algorithm is invariant to rotation  translation and scale variation. But it is a timeconsuming algorithm. The wasting time is related to image size. So the proposed algorithm first adopts mean shift to initially locate object position  then SIFT operator is used to detect features in object area and model area  lastly  the proposed method matches features in these two areas and calculates the relationship between them using affine transform. According to affine transform parameters  the state of object can be adjusted in time. In order to reduce process time  an improved feature matching algorithm is proposed in this paper. Experiments show that the proposed algorithm deals with occlusion successfully and can adjust object size in time. 2008 IEEE.  
宽基线立体图像的区域匹配及应用 学位论文  OAI收割
工学硕士, 中国科学院自动化研究所: 中国科学院研究生院, 2007
宋小丽
收藏  |  浏览/下载:77/0  |  提交时间:2015/09/02