SIA OpenIR  > 光电信息技术研究室
MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images
Wang ED(王恩德)1; Jiang, Yanmei2,3; Li Y(李勇)1,4; Yang, Jingchao2; Ren, Mengcheng4; Zhang, Qingchun4
Department光电信息技术研究室
Source PublicationAPPLIED SCIENCES-BASEL
ISSN2076-3417
2019
Volume9Issue:19Pages:1-18
Indexed BySCI
WOS IDWOS:000496258100101
Contribution Rank1
Funding OrganizationNatural Science Young Foundation of Hebei Provincial Department of Education [QN2017324]
KeywordSemantic segmentation remote sensing images feature fusion cost-sensitive
Abstract

Semantic segmentation of remote sensing images is an important technique for spatial analysis and geocomputation. It has important applications in the fields of military reconnaissance, urban planning, resource utilization and environmental monitoring. In order to accurately perform semantic segmentation of remote sensing images, we proposed a novel multi-scale deep features fusion and cost-sensitive loss function based segmentation network, named MFCSNet. To acquire the information of different levels in remote sensing images, we design a multi-scale feature encoding and decoding structure, which can fuse the low-level and high-level semantic information. Then a max-pooling indices up-sampling structure is designed to improve the recognition rate of the object edge and location information in the remote sensing image. In addition, the cost-sensitive loss function is designed to improve the classification accuracy of objects with fewer samples. The penalty coefficient of misclassification is designed to improve the robustness of the network model, and the batch normalization layer is also added to make the network converge faster. The experimental results show that the classification performance of MFCSNet outperforms U-Net and SegNet in classification accuracy, object details and prediction consistency.

Language英语
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/25888
Collection光电信息技术研究室
Corresponding AuthorJiang, Yanmei; Li Y(李勇)
Affiliation1.Key Laboratory of Optical Electrical Image Processing, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Department of Electrical and Information Engineering, Hebei Jiaotong Vocational and Technical College, Shijiazhuang 050000, China
3.State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China
4.College of Information Science and Engineering, Northeastern University, Shenyang 110819, China
Recommended Citation
GB/T 7714
Wang ED,Jiang, Yanmei,Li Y,et al. MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images[J]. APPLIED SCIENCES-BASEL,2019,9(19):1-18.
APA Wang ED,Jiang, Yanmei,Li Y,Yang, Jingchao,Ren, Mengcheng,&Zhang, Qingchun.(2019).MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images.APPLIED SCIENCES-BASEL,9(19),1-18.
MLA Wang ED,et al."MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images".APPLIED SCIENCES-BASEL 9.19(2019):1-18.
Files in This Item: Download All
File Name/Size DocType Version Access License
MFCSNet_ Multi-Scale(9881KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang ED(王恩德)]'s Articles
[Jiang, Yanmei]'s Articles
[Li Y(李勇)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang ED(王恩德)]'s Articles
[Jiang, Yanmei]'s Articles
[Li Y(李勇)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang ED(王恩德)]'s Articles
[Jiang, Yanmei]'s Articles
[Li Y(李勇)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MFCSNet_ Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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