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:
Geometric moment invariants to spatial transform and N-fold symmetric blur 期刊论文  OAI收割
PATTERN RECOGNITION, 2021, 卷号: 115, 页码: 14
作者:  
Mo, Hanlin;  Hao, Hongxiang;  Li, Hua
  |  收藏  |  浏览/下载:25/0  |  提交时间:2021/12/01
Densely connected Siamese network visual tracking 期刊论文  OAI收割
INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2021
作者:  
Zhou, Xiaolong;  Wang, Pinghao;  Chan, Sixian;  Fang, Kai;  Fang, Jianwen
  |  收藏  |  浏览/下载:72/0  |  提交时间:2021/08/31
Robust Object Tracking via Information Theoretic Measures 期刊论文  OAI收割
International Journal of Automation and Computing, 2020, 卷号: 17, 期号: 5, 页码: 652-666
作者:  
Wei-Ning Wang;  Qi Li;  Liang Wang
  |  收藏  |  浏览/下载:12/0  |  提交时间:2021/02/22
Study on the Classification of LAMOST Early Stellar Spectrum Template by Mahalanobis Distance 期刊论文  OAI收割
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 卷号: 39, 期号: 5, 页码: 1618-1622
作者:  
Chen Shu-xin;  Sun Wei-min;  Song Yi-han
  |  收藏  |  浏览/下载:57/0  |  提交时间:2020/03/10
Siamese Tracking with Adaptive Template-Updating Strategy 期刊论文  OAI收割
APPLIED SCIENCES-BASEL, 2019, 卷号: 9, 期号: 18, 页码: 1-17
作者:  
Chang Z(常铮);  Xu Z(徐峥);  Hui B(惠斌);  Ju MR(鞠默然);  Luo HB(罗海波)
  |  收藏  |  浏览/下载:36/0  |  提交时间:2019/11/13
Similarity Measurement Among Classification Templates for LAMOST Stellar Spectra 期刊论文  OAI收割
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 卷号: 38, 期号: 6, 页码: 1922-1925
作者:  
Chen Shu-xin;  Sun Wei-min;  Kong Xiao
  |  收藏  |  浏览/下载:9/0  |  提交时间:2020/03/10
Dual Efficient Second-order Minimization Method for Template-based Visual Tracking 会议论文  OAI收割
International Symposium on Infrared Technology and Application and the International Symposiums on Robot Sensing and Advanced Control, Beijing, May 9-11, 2016
作者:  
Li CX(李晨曦);  Shi ZL(史泽林);  Liu YP(刘云鹏)
收藏  |  浏览/下载:31/0  |  提交时间:2016/09/13
Similarity learning for object recognition based on derived kernel 期刊论文  OAI收割
neurocomputing, 2012, 卷号: 83, 页码: 110-120
作者:  
Li, Hong;  Wei, Yantao;  Li, Luoqing;  Yuan, Yuan
收藏  |  浏览/下载:37/0  |  提交时间:2012/09/03
Partial occlusion detection of object boundary (EI CONFERENCE) 会议论文  OAI收割
2009 IEEE Intrumentation and Measurement Technology Conference, I2MTC 2009, May 5, 2009 - May 7, 2009, Singapore, Singapore
作者:  
Zhang J.;  Zhang K.;  Zhang K.;  Zhang K.;  Zhang K.
收藏  |  浏览/下载:32/0  |  提交时间:2013/03/25
Partial occlusion is a difficult problem in computer vision since whether the object is changed or occluded is ambiguous  especially when distinguishing it only from the object boundary. In this paper  we proposed a novel idea to solve this problem by taking shape matching as a morphing processing. A mass-spring model is constructed from the point set which is sampled from a template (or reference) object boundary by moving it to a target object which is deformed and/or occluded. From the morphing processing  sufficient information can be obtained and an accurate detection of occlusion is performed. By using of the proposed method  the application scope of occlusion detection is expanded while other method cannot be performed which need color  texture  or motion information. The experiments performed on synthetic and real world images proved the satisfactory performance of the proposed method. 2009 IEEE.  
Affine object recognition and affine parameters estimation based on covariant matrix (EI CONFERENCE) 会议论文  OAI收割
2008 International Symposium on Information Science and Engineering, ISISE 2008, December 20, 2008 - December 22, 2008, Shanghai, China
作者:  
Wang Y.;  Wang Y.;  Wang Y.;  Wang Y.;  Wang Y.
收藏  |  浏览/下载:145/0  |  提交时间:2013/03/25
A new method of affine object recognition and affine parameters estimation is presented. For a real-time image and a group of templates  in addition  firstly  on the basis of correct recognition  we segment the object regions in them and compute their covariant matrices. Secondly  it can estimate affine parameters exactly  normalize the ellipse regions defined by covariant matrices to circle regions to get rotational invariants  and the estimated error is within 3%. 2008 IEEE.  and compute the similarity function value between rotational invariants of real-time image and every template respectively. Then compare the values with threshold set in advance  if more than one value is larger than threshold  take the corresponding templates as candidates  and compute affine matrix between real-time image and every candidate. Finally  transform the realtime image with every affine matrix and match the result with corresponding candidate by classical matching methods. Experimental results show that the presented method is robust to illumination  with low computational complexity  and it can realize recognition of different affine objects