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
2018-04-01
发表期刊PATTERN RECOGNITION
卷号76期号:76页码:288-302
文章类型Article
摘要To 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.
关键词Image Based Modeling Ground-to-aerial Model Alignment Ground-to-aerial Image Matching
WOS标题词Science & Technology ; Technology
DOI10.1016/j.patcog.2017.11.003
关键词[WOS]OBJECT RECOGNITION ; 3D RECONSTRUCTION ; REGISTRATION ; FEATURES ; SCENES
收录类别SCI
语种英语
项目资助者National Science Foundation of China (NSFC)(61333015 ; Doctoral Research Grant of Taiyuan University of Science Technology(20162009) ; 61421004 ; 61632003 ; 61402316)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000424853800022
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21738
专题模式识别国家重点实验室_机器人视觉
作者单位1.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
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
PR2018.pdf(6450KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Gao, Xiang]的文章
[Hu, Lihua]的文章
[Cui, Hainan]的文章
百度学术
百度学术中相似的文章
[Gao, Xiang]的文章
[Hu, Lihua]的文章
[Cui, Hainan]的文章
必应学术
必应学术中相似的文章
[Gao, Xiang]的文章
[Hu, Lihua]的文章
[Cui, Hainan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: PR2018.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。