SIA OpenIR  > 光电信息技术研究室
Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold
Liu TC(刘天赐)1,2,3,4,5; Shi ZL(史泽林)1,2,4,5; Liu YP(刘云鹏)1,2,4,5
Department光电信息技术研究室
Source PublicationIEEE Access
ISSN2169-3536
2019
Volume7Pages:105531-105545
Indexed BySCI ; EI
EI Accession number20193507363977
WOS IDWOS:000481972100012
Contribution Rank1
Funding OrganizationInnovation Fund of Chinese Academy of Sciences
KeywordGeometric transformation visualization motion group Riemannian manifold
AbstractGeometric transformations of images are the predominant factor, which influences the effectiveness of visual tracking and detection tasks in computer vision. Naturally, although it makes significant sense to grasp the process of image geometric transformations, the numerical relationship of geometric transformations cannot be revealed directly from images themselves. Even if the geometric transformation matrices form the three-dimensional special linear group, Sl(3,) group, it is difficult to comprehend the manifold of this invisible visual motion, which resides in the high-dimensional space. Furthermore, the main challenge is the deficiency of analytic expressions of the Riemannian logarithmic map to compute the geodesic distance on the Sl(3,) manifold. Facing these issues, this paper comes up with a novel approach to visualize the geometric transformation in images by presenting a new metric, and then, computes a set of coordinate-vectors in the three-dimensional state transition space for visualization using the Riemannian stress majorization. The superiority of the presented framework for visualization, in terms of accuracy and efficiency, is demonstrated through abundant experiments on aerial images and moving objects.
Language英语
WOS SubjectComputer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS KeywordDIMENSIONALITY REDUCTION ; ALGORITHM
WOS Research AreaComputer Science ; Engineering ; Telecommunications
Funding ProjectInnovation Fund of Chinese Academy of Sciences[Y8K4160401] ; Innovation Fund of Chinese Academy of Sciences[Y8K4160401]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/25511
Collection光电信息技术研究室
Corresponding AuthorLiu TC(刘天赐); Shi ZL(史泽林)
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang 110016, China
5.Key Laboratory of Image Understanding and Computer Vision, Shenyang 110016, China
Recommended Citation
GB/T 7714
Liu TC,Shi ZL,Liu YP. Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold[J]. IEEE Access,2019,7:105531-105545.
APA Liu TC,Shi ZL,&Liu YP.(2019).Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold.IEEE Access,7,105531-105545.
MLA Liu TC,et al."Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold".IEEE Access 7(2019):105531-105545.
Files in This Item: Download All
File Name/Size DocType Version Access License
Visualization of the(2344KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu TC(刘天赐)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Liu YP(刘云鹏)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu TC(刘天赐)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Liu YP(刘云鹏)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu TC(刘天赐)]'s Articles
[Shi ZL(史泽林)]'s Articles
[Liu YP(刘云鹏)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Visualization of the Image Geometric Transformation Group Based on Riemannian Manifold.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.