SIA OpenIR  > 机器人学研究室
A multi-domain feature learning method for visual place recognition
Yin P(殷鹏)1; Xu LY(许凌云)1; Li, Xueqian3; Yin, Chen4; Li YL(李英立)1; Srivatsan, Rangaprasad Arun3; Li, Lu3; Ji JM(吉建民)2; He YQ(何玉庆)1
Department机器人学研究室
Conference Name2019 International Conference on Robotics and Automation, ICRA 2019
Conference DateMay 20-24, 2019
Conference PlaceMontreal, QC, Canada
Author of SourceBosch ; DJI ; et al. ; Kinova ; Mercedes-Benz ; Samsung
Source Publication2019 International Conference on Robotics and Automation, ICRA 2019
PublisherIEEE
Publication PlaceNew York
2019
Pages319-324
Indexed ByEI ; CPCI(ISTP)
EI Accession number20193507383961
WOS IDWOS:000494942300040
Contribution Rank1
ISSN1050-4729
ISBN978-1-5386-6026-3
AbstractVisual Place Recognition (VPR) is an important component in both computer vision and robotics applications, thanks to its ability to determine whether a place has been visited and where specifically. A major challenge in VPR is to handle changes of environmental conditions including weather, season and illumination. Most VPR methods try to improve the place recognition performance by ignoring the environmental factors, leading to decreased accuracy decreases when environmental conditions change significantly, such as day versus night. To this end, we propose an end-to-end conditional visual place recognition method. Specifically, we introduce the multi-domain feature learning method (MDFL) to capture multiple attribute-descriptions for a given place, and then use a feature detaching module to separate the environmental condition-related features from those that are not. The only label required within this feature learning pipeline is the environmental condition. Evaluation of the proposed method is conducted on the multi-season NORDLAND dataset, and the multi-weather GTAV dataset. Experimental results show that our method improves the feature robustness against variant environmental conditions.
Language英语
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/25515
Collection机器人学研究室
Corresponding AuthorYin P(殷鹏); Ji JM(吉建民)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China
2.School of Computer Science and Technology, University of Science and Technology, Hefei, China
3.Biorobotics Lab, Robotics Institute, Carnegie Mellon University, Pittsburgh
4.PA
5.15213, United States
6.School of Computer Science, University of Beijing University of Posts and Telecommunications, Beijing, China
Recommended Citation
GB/T 7714
Yin P,Xu LY,Li, Xueqian,et al. A multi-domain feature learning method for visual place recognition[C]//Bosch, DJI, et al., Kinova, Mercedes-Benz, Samsung. New York:IEEE,2019:319-324.
Files in This Item:
File Name/Size DocType Version Access License
A multi-domain featu(289KB)会议论文 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
[Yin P(殷鹏)]'s Articles
[Xu LY(许凌云)]'s Articles
[Li, Xueqian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yin P(殷鹏)]'s Articles
[Xu LY(许凌云)]'s Articles
[Li, Xueqian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yin P(殷鹏)]'s Articles
[Xu LY(许凌云)]'s Articles
[Li, Xueqian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A multi-domain feature learning method for visual place recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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