中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery

文献类型：期刊论文

作者Wang, Yong1; Zeng, Xiangqiang1,2; Liao, Xiaohan1; Zhuang, Dafang1
刊名REMOTE SENSING
出版日期2022
卷号14期号:2页码:24
关键词deep learning building extraction spatial attention global information awareness cross level information fusion
DOI10.3390/rs14020269
通讯作者Wang, Yong(wangy@igsnrr.ac.cn)
英文摘要Deep learning (DL) shows remarkable performance in extracting buildings from high resolution remote sensing images. However, how to improve the performance of DL based methods, especially the perception of spatial information, is worth further study. For this purpose, we proposed a building extraction network with feature highlighting, global awareness, and cross level information fusion (B-FGC-Net). The residual learning and spatial attention unit are introduced in the encoder of the B-FGC-Net, which simplifies the training of deep convolutional neural networks and highlights the spatial information representation of features. The global feature information awareness module is added to capture multiscale contextual information and integrate the global semantic information. The cross level feature recalibration module is used to bridge the semantic gap between low and high level features to complete the effective fusion of cross level information. The performance of the proposed method was tested on two public building datasets and compared with classical methods, such as UNet, LinkNet, and SegNet. Experimental results demonstrate that B-FGC-Net exhibits improved profitability of accurate extraction and information integration for both small and large scale buildings. The IoU scores of B-FGC-Net on WHU and INRIA Building datasets are 90.04% and 79.31%, respectively. B-FGC-Net is an effective and recommended method for extracting buildings from high resolution remote sensing images.
WOS关键词SEMANTIC SEGMENTATION ; NEURAL-NETWORKS ; ATTENTION
资助项目Strategic Priority Research Program of Chinese Academy of Sciences[XDA28050200] ; Third Xinjiang Scientific Expedition Program[2021xjkk1402] ; Major Special Project--the China High resolution Earth Observation System[30-Y30F06-9003-20/22] ; Fujian Province Highway Science and Technology Project: Key technology of Intelligent Inspection of Highway UAV Network by Remote Sensing[GS 202101]
WOS研究方向Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000758689700001
出版者MDPI
资助机构Strategic Priority Research Program of Chinese Academy of Sciences ; Third Xinjiang Scientific Expedition Program ; Major Special Project--the China High resolution Earth Observation System ; Fujian Province Highway Science and Technology Project: Key technology of Intelligent Inspection of Highway UAV Network by Remote Sensing
源URL[http://ir.igsnrr.ac.cn/handle/311030/171148]  
专题中国科学院地理科学与资源研究所
通讯作者Wang, Yong
作者单位1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Yong,Zeng, Xiangqiang,Liao, Xiaohan,et al. B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery[J]. REMOTE SENSING,2022,14(2):24.
APA Wang, Yong,Zeng, Xiangqiang,Liao, Xiaohan,&Zhuang, Dafang.(2022).B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery.REMOTE SENSING,14(2),24.
MLA Wang, Yong,et al."B-FGC-Net: A Building Extraction Network from High Resolution Remote Sensing Imagery".REMOTE SENSING 14.2(2022):24.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

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。