OPT OpenIR  > 光学影像学习与分析中心
Bidirectional adaptive feature fusion for remote sensing scene classification
Lu, Xiaoqiang1; Ji, Weijun1,2; Li, Xuelong1,2; Zheng, Xiangtao1
Department光学影像学习与分析中心
2019-02-07
Source PublicationNEUROCOMPUTING
ISSN0925-2312;1872-8286
Volume328Issue:SIPages:135-146
Contribution Rank1
Abstract

Scene classification has become an effective way to interpret the High Spatial Resolution (HSR) remote sensing images. Recently, Convolutional Neural Networks (CNN) have been found to be excellent for scene classification. However, only using the deep models as feature extractor on the aerial image directly is not proper, because the extracted deep features can not capture spatial scale variability and rotation variability in HSR remote sensing images. To relieve this limitation, a bidirectional adaptive feature fusion strategy is investigated to deal with the remote sensing scene classification. The deep learning feature and the SIFT feature are fused together to get a discriminative image presentation. The fused feature can not only describe the scenes effectively by employing deep learning feature but also overcome the scale and rotation variability with the usage of the SIFT feature. By fusing both SIFT feature and global CNN feature, our method achieves state-of-the-art scene classification performances on the UCMerced, the Sydney and the AID datasets. (C) 2018 Elsevier B.V. All rights reserved.

KeywordBidirectional adaptive feature fusion High spatial resolution remote Sensing images Scene classification
DOI10.1016/j.neucom.2018.03.076
Indexed BySCI
Language英语
WOS IDWOS:000458065600015
PublisherELSEVIER SCIENCE BV
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/31157
Collection光学影像学习与分析中心
Corresponding AuthorLu, Xiaoqiang
Affiliation1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China
2.Univ Chinese Acad Sci, 19A Yuquanlu, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Lu, Xiaoqiang,Ji, Weijun,Li, Xuelong,et al. Bidirectional adaptive feature fusion for remote sensing scene classification[J]. NEUROCOMPUTING,2019,328(SI):135-146.
APA Lu, Xiaoqiang,Ji, Weijun,Li, Xuelong,&Zheng, Xiangtao.(2019).Bidirectional adaptive feature fusion for remote sensing scene classification.NEUROCOMPUTING,328(SI),135-146.
MLA Lu, Xiaoqiang,et al."Bidirectional adaptive feature fusion for remote sensing scene classification".NEUROCOMPUTING 328.SI(2019):135-146.
Files in This Item:
File Name/Size DocType Version Access License
Bidirectional adapti(3917KB)期刊论文出版稿开放获取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
[Lu, Xiaoqiang]'s Articles
[Ji, Weijun]'s Articles
[Li, Xuelong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lu, Xiaoqiang]'s Articles
[Ji, Weijun]'s Articles
[Li, Xuelong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lu, Xiaoqiang]'s Articles
[Ji, Weijun]'s Articles
[Li, Xuelong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Bidirectional adaptive feature fusion for remote sensing scene classification.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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