SIA OpenIR  > 其他
Efficient and robust unsupervised inverse intensity compensation for stereo image registration under radiometric changes
Xu, Chenglong1,3; Wu CD(吴成东)1; Qu DK(曲道奎)2,3; Sun HB(孙海波)1,2; Song JL(宋吉来)2,3
Department其他
Source PublicationSIGNAL PROCESSING-IMAGE COMMUNICATION
ISSN0923-5965
2021
Volume90Pages:1-11
Indexed BySCI
WOS IDWOS:000595038700013
Contribution Rank2
Funding OrganizationNational Key R&D Program of China Foundation [2017YFB1304100] ; Major Scientific and Technological Innovation Project of Shandong Province [2019JZZY01012] ; Research and development of key technologies for hybrid robot of Liaoning Province [XLYC1907110]
KeywordImage registration 5-D vector Photometric changes Intensity compensation RGB-Gradient tree
Abstract

Image registration is a challenging problem for computer vision, and accurate and effective image registration is still required in various computer vision applications, e.g., 3-D scanning, autonomous navigation, and augmented reality. However, image registration becomes difficult due to the presence of noise and photometric changes. This paper presents a novel image registration method with unsupervised inverse intensity compensation (ICIR). This methodology uses weighted vectors to compensate for areas affected by radiometric variations. This is a 5-D vector body composed of RGB, brightness, and gradient, that is, each pixel is represented by a 5-D vector in its neighborhood. When performing image registration, the vector angle metric robust to illumination effect is used to calculate cost volumes. Then the selected cost metrics are aggregated based on RGB-Gradient tree structure. Experiments performed on stereo images of the Middlebury datasets and ours demonstrate this methodology in calculation accuracy and time all have good performance.

Language英语
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28145
Collection其他
Corresponding AuthorWu CD(吴成东)
Affiliation1.Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110169, China
2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110169, China
3.Shenyang SIASUN Robot & Automation Co., LTD., Shenyang 110169, China
Recommended Citation
GB/T 7714
Xu, Chenglong,Wu CD,Qu DK,et al. Efficient and robust unsupervised inverse intensity compensation for stereo image registration under radiometric changes[J]. SIGNAL PROCESSING-IMAGE COMMUNICATION,2021,90:1-11.
APA Xu, Chenglong,Wu CD,Qu DK,Sun HB,&Song JL.(2021).Efficient and robust unsupervised inverse intensity compensation for stereo image registration under radiometric changes.SIGNAL PROCESSING-IMAGE COMMUNICATION,90,1-11.
MLA Xu, Chenglong,et al."Efficient and robust unsupervised inverse intensity compensation for stereo image registration under radiometric changes".SIGNAL PROCESSING-IMAGE COMMUNICATION 90(2021):1-11.
Files in This Item:
File Name/Size DocType Version Access License
Efficient and robust(5732KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xu, Chenglong]'s Articles
[Wu CD(吴成东)]'s Articles
[Qu DK(曲道奎)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xu, Chenglong]'s Articles
[Wu CD(吴成东)]'s Articles
[Qu DK(曲道奎)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xu, Chenglong]'s Articles
[Wu CD(吴成东)]'s Articles
[Qu DK(曲道奎)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Efficient and robust unsupervised inverse intensity compensation for stereo image registration under radiometric changes.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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