CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Accurate and efficient ground-to-aerial model alignment
Gao, Xiang1,2; Hu, Lihua4; Cui, Hainan1; Shen, Shuhan1,2; Hu, Zhanyi1,2,3
AbstractTo produce a complete 3D reconstruction of a large-scale architectural scene, both ground and aerial images are usually captured. A common approach is to first reconstruct the models from different image sources separately, and align thetn afterwards. Using this pipeline, this work proposes an accurate and efficient approach for ground-to-aerial model alignment in a coarse-to-fine manner. First, both the ground model and aerial model are transformed into the geo-referenced coordinate system using GPS meta-information for coarse alignment. Then, the coarsely aligned models are refined by a similarity transformation that is estimated based on 3D point correspondences between them, and the 3D point correspondences are determined in a 2D-image-matching manner by considering the rich textural and contextual information in the 2D images. Due to the dramatic differences in viewpoint and scale between ground and aerial images, which make matching them directly nearly impossible, we perform an intermediate view-synthesis step to mitigate the matching difficulty. To this end, the following three key issues are addressed: (a) selecting a suitable subset of aerial images to cover the ground model properly; (b) synthesizing images from the ground model under the viewpoints of the selected aerial images; and finally, (c) obtaining the 2D point matches between the synthesized images and the selected aerial images. The experimental results show that the proposed model alignment approach is quite effective and outperforms several state-of-the-art techniques in terms of both accuracy and efficiency. (C) 2017 Elsevier Ltd. All rights reserved.
KeywordImage Based Modeling Ground-to-aerial Model Alignment Ground-to-aerial Image Matching
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Science Foundation of China (NSFC)(61333015 ; Doctoral Research Grant of Taiyuan University of Science Technology(20162009) ; 61421004 ; 61632003 ; 61402316)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000424853800022
Citation statistics
Cited Times:11[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100049, Peoples R China
4.Taiyuan Univ Sci & Technol, Sch Comp Sci & Technol, Taiyuan 030024, Shanxi, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Gao, Xiang,Hu, Lihua,Cui, Hainan,et al. Accurate and efficient ground-to-aerial model alignment[J]. PATTERN RECOGNITION,2018,76(76):288-302.
APA Gao, Xiang,Hu, Lihua,Cui, Hainan,Shen, Shuhan,&Hu, Zhanyi.(2018).Accurate and efficient ground-to-aerial model alignment.PATTERN RECOGNITION,76(76),288-302.
MLA Gao, Xiang,et al."Accurate and efficient ground-to-aerial model alignment".PATTERN RECOGNITION 76.76(2018):288-302.
Files in This Item: Download All
File Name/Size DocType Version Access License
PR2018.pdf(6450KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gao, Xiang]'s Articles
[Hu, Lihua]'s Articles
[Cui, Hainan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gao, Xiang]'s Articles
[Hu, Lihua]'s Articles
[Cui, Hainan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gao, Xiang]'s Articles
[Hu, Lihua]'s Articles
[Cui, Hainan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PR2018.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.

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