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
MSF-Net: A Multiscale Supervised Fusion Network for Building Change Detection in High-Resolution Remote Sensing Images

文献类型：期刊论文

作者Chen, Jiahao2; Fan, Junfu1,2,3; Zhang, Mengzhen2; Zhou, Yuke4; Shen, Chen1,3
刊名IEEE ACCESS
出版日期2022
卷号10页码:30925-30938
关键词Buildings Feature extraction Decoding Remote sensing Fuses Encoding Convolution Remote sensing building change detection deep learning attention mechanism multiscale feature
ISSN号2169-3536
DOI10.1109/ACCESS.2022.3160163
通讯作者Fan, Junfu(fanjf@sdut.edu.cn) ; Zhou, Yuke(zhouyk@igsnrr.ac.cn)
英文摘要Building change detection is a primary task in the application of remote sensing images, especially in city land resource management and urbanization process assesment. Due to the rich textural features of remote sensing images and the multiscale characteristics of buildings, it is still a huge challenge to effectively filter out irrelevant change information (e.g., roads) and fuse multiscale building features. To date, deep learning-based methods have demonstrated powerful capabilities in this field. To fill these gaps, this study proposes a multiscale supervised fusion network (MSF-Net), which is an attention mechanism-based approach for building change detection using bi-temporal high-resolution satellite imagery. Especially, we built a dual-context fusion module to obtain abundant global context information of buildings and suppressing irrelevant features. We also used channel attention mechanism, selective kernel convolution and multiscale supervision module to fuse multiscale feature of buildings. The ablation experiments verified the availability of these modules. The MSF-Net model has been tested on the LEVIR-CD building change detection dataset. Compared with other state-of-the-art change detection methods, the study showed that our method obtained 0.8866 and 0.8130 in F1-score and Intersection over Union (IOU), respectively. The results indicate that the MSF-Net method has stronger multiscale building feature extraction capability and suppression ability of irrelevant features, which could produce clearer building boundaries and more accurate building change maps.
WOS关键词NEURAL-NETWORK ; CNN ; ATTENTION ; MODEL
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:000773243800001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://ir.igsnrr.ac.cn/handle/311030/173491]  
专题中国科学院地理科学与资源研究所
通讯作者Fan, Junfu; Zhou, Yuke
作者单位1.High Resolut Earth Observat Syst Data & Applicat, Zibo 255000, Shandong, Peoples R China
2.Shandong Univ Technol, Sch Civil & Architectural Engn, Zibo 255000, Shandong, Peoples R China
3.Shandong Tianyunhe Informat Technol Co Ltd, Zibo 255000, Shandong, Peoples R China
4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Ecol Observing Network & Modeling Lab, Beijing 100101, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Jiahao,Fan, Junfu,Zhang, Mengzhen,et al. MSF-Net: A Multiscale Supervised Fusion Network for Building Change Detection in High-Resolution Remote Sensing Images[J]. IEEE ACCESS,2022,10:30925-30938.
APA Chen, Jiahao,Fan, Junfu,Zhang, Mengzhen,Zhou, Yuke,&Shen, Chen.(2022).MSF-Net: A Multiscale Supervised Fusion Network for Building Change Detection in High-Resolution Remote Sensing Images.IEEE ACCESS,10,30925-30938.
MLA Chen, Jiahao,et al."MSF-Net: A Multiscale Supervised Fusion Network for Building Change Detection in High-Resolution Remote Sensing Images".IEEE ACCESS 10(2022):30925-30938.

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。