题名 | Deep Homography Estimation for Visual Place Recognition |
作者 | |
通讯作者 | Lan, Xiangyuan; Yuan, Chun |
DOI | |
发表日期 | 2024-03-25
|
会议名称 | 38th AAAI Conference on Artificial Intelligence, AAAI 2024
|
ISSN | 2159-5399
|
EISSN | 2374-3468
|
ISBN | 9781577358879
|
会议录名称 | |
卷号 | 38
|
页码 | 10341-10349
|
会议日期 | February 20, 2024 - February 27, 2024
|
会议地点 | Vancouver, BC, Canada
|
会议录编者/会议主办者 | Association for the Advancement of Artificial Intelligence
|
出版地 | 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA
|
出版者 | |
摘要 | Visual place recognition (VPR) is a fundamental task for many applications such as robot localization and augmented reality. Recently, the hierarchical VPR methods have received considerable attention due to the trade-off between accuracy and efficiency. They usually first use global features to retrieve the candidate images, then verify the spatial consistency of matched local features for re-ranking. However, the latter typically relies on the RANSAC algorithm for fitting homography, which is time-consuming and non-differentiable. This makes existing methods compromise to train the network only in global feature extraction. Here, we propose a transformer-based deep homography estimation (DHE) network that takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Moreover, we design a re-projection error of inliers loss to train the DHE network without additional homography labels, which can also be jointly trained with the backbone network to help it extract the features that are more suitable for local matching. Extensive experiments on benchmark datasets show that our method can outperform several state-of-the-art methods. And it is more than one order of magnitude faster than the mainstream hierarchical VPR methods using RANSAC. The code is released at https://github.com/Lu-Feng/DHE-VPR. Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. |
学校署名 | 其他
|
语种 | 英语
|
相关链接 | [来源记录] |
收录类别 | |
资助项目 | This work was supported by the National Key R&D Program of China (2022YFB4701400/4701402), SSTIC Grant (JCYJ20190809172201639, WDZC20200820200655001), Shenzhen Key Laboratory (ZDSYS20210623092001004), the Project of Peng Cheng Laboratory (PCL2023A08), and Beijing Key Lab of Networked Multimedia.
|
WOS研究方向 | Computer Science
; Mathematics
; Robotics
|
WOS类目 | Computer Science, Artificial Intelligence
; Computer Science, Theory & Methods
; Mathematics, Applied
; Robotics
|
WOS记录号 | WOS:001241512400104
|
EI入藏号 | 20241515853836
|
EI主题词 | Economic and social effects
; Robot applications
|
EI分类号 | Computer Software, Data Handling and Applications:723
; Robot Applications:731.6
; Social Sciences:971
|
来源库 | EV Compendex
|
引用统计 | |
成果类型 | 会议论文 |
条目标识符 | http://sustech.caswiz.com/handle/2SGJ60CL/794529 |
专题 | 南方科技大学 |
作者单位 | 1.Tsinghua Shenzhen International Graduate School, Tsinghua University, China 2.Peng Cheng Laboratory, China 3.Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, China 4.Southern University of Science and Technology, China |
推荐引用方式 GB/T 7714 |
Lu, Feng,Dong, Shuting,Zhang, Lijun,et al. Deep Homography Estimation for Visual Place Recognition[C]//Association for the Advancement of Artificial Intelligence. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:Association for the Advancement of Artificial Intelligence,2024:10341-10349.
|
条目包含的文件 | 条目无相关文件。 |
|
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。
修改评论