ShanghaiTech University Knowledge Management System
| Weakly-supervised Camera Localization by Ground-to-satellite Image Registration | |
| 2024-09-10 | |
| 会议录名称 | ARXIV (IF:0.402[JCR-2005],0.000[5-Year]) |
| ISSN | 0302-9743 |
| 卷号 | 15067 |
| 发表状态 | 已发表 |
| DOI | arXiv:2409.06471 |
| 摘要 | The ground-to-satellite image matching/retrieval was initially proposed for city-scale ground camera localization. This work addresses the problem of improving camera pose accuracy by ground-to-satellite image matching after a coarse location and orientation have been obtained, either from the city-scale retrieval or from consumer-level GPS and compass sensors. Existing learning-based methods for solving this task require accurate GPS labels of ground images for network training. However, obtaining such accurate GPS labels is difficult, often requiring an expensive Real Time Kinematics (RTK) setup and suffering from signal occlusion, multi-path signal disruptions, etc. . To alleviate this issue, this paper proposes a weakly supervised learning strategy for ground-to-satellite image registration when only noisy pose labels for ground images are available for network training. It derives positive and negative satellite images for each ground image and leverages contrastive learning to learn feature representations for ground and satellite images useful for translation estimation. We also propose a self-supervision strategy for cross-view image relative rotation estimation, which trains the network by creating pseudo query and reference image pairs. Experimental results show that our weakly supervised learning strategy achieves the best performance on cross-area evaluation compared to recent state-of-the-art methods that are reliant on accurate pose labels for supervision. |
| 关键词 | Ground-to-satellite image matching Cross-view image matching Weakly-supervised camera localization |
| 会议名称 | 18th European Conference on Computer Vision (ECCV) |
| 出版地 | GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND |
| 会议地点 | null,Milan,ITALY |
| 会议日期 | SEP 29-OCT 04, 2024 |
| URL | 查看原文 |
| 收录类别 | PPRN.PPRN |
| 语种 | 英语 |
| 资助项目 | ARC Discovery Grant[DP220100800] |
| WOS研究方向 | Computer Science |
| WOS类目 | Computer Science, Software Engineering |
| WOS记录号 | PPRN:91823112 |
| 出版者 | SPRINGER INTERNATIONAL PUBLISHING AG |
| EISSN | 1611-3349 |
| 文献类型 | 会议论文 |
| 条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/427474 |
| 专题 | 信息科学与技术学院_PI研究组_师玉娇组 |
| 通讯作者 | Shi, Yujiao |
| 作者单位 | 1.ShanghaiTech Univ, Shanghai, Peoples R China 2.Australian Natl Univ, Canberra, Australia 3.Ford Motor Co, Dearborn, MI, USA |
| 第一作者单位 | 上海科技大学 |
| 通讯作者单位 | 上海科技大学 |
| 第一作者的第一单位 | 上海科技大学 |
| 推荐引用方式 GB/T 7714 | Shi, Yujiao,Li, Hongdong,Perincherry, Akhil,et al. Weakly-supervised Camera Localization by Ground-to-satellite Image Registration[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2024. |
| 条目包含的文件 | ||||||
| 条目无相关文件。 | ||||||
修改评论
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。