Knowledge management system National Space Science Center,CAS
A new deep learning method for roads recognition from SAR images | |
Alternative Title | 20204109338002 |
Chen, Hua1,2,3; Guo, Wei1,2; Yan, Jing-Wen4; Zhuo, Wen-Hao4; Wu, Liang-Bin5 | |
Source Publication | Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)
![]() |
2020 | |
Volume | 50Issue:5Pages:1778-1787 |
DOI | 10.13229/j.cnki.jdxbgxb20190490 |
ISSN | 16715497 |
Language | 中文 |
Keyword | Convolution - Deep learning - Image enhancement - Learning systems - Neural networks - Remote sensing - Roads and streets - Support vector machines - Synthetic aperture radar Activation functions - Convolution neural network - Learning methods - Overall characteristics - Recognition accuracy - Remote sensing images - Road recognition - Synthetic aperture radar (SAR) images |
Abstract | Deep learning is an effective technical method to enhance the recognition accuracy of remote sensing image target. To solve the problem of the complicated steps in road recognition from Synthetic Aperture Radar(SAR) images, this paper proposes a SAR image road recognition method based on deep learning. First, based on the traditional Full Convolution Neural Network(FCNN), a New Convolution Neural Network(NCNN) is constructed by revising the activation function to effectively alleviate the loss of road information. Then, the NCNN is applied to road recognition experiments of simulated SAR images and real SAR images with self-constructed road label sets to improve the robustness of the proposed method. The experimental results show that the NCNN can be used to identify the overall characteristics of the road with higher accuracy and better reliability in comparison with the Support Vector Machine(SVM), traditional FCNN and other algorithms. © 2020, Jilin University Press. All right reserved. |
Indexed By | EI |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.nssc.ac.cn/handle/122/7473 |
Collection | 中国科学院国家空间科学中心 |
Affiliation | 1.Key Laboratory of Microwave Remote Sensing, Chinese Academy of Sciences, Beijing; 100190, China; 2.National Space Science Center, Chinese Academy of Sciences, Beijing; 100190, China; 3.Graduate School of University of Chinese Academy of Sciences, Beijing; 100049, China; 4.College of Engineering, Shantou University, Shantou; 515063, China; 5.Radar and Electronic Equipment Research Institute of China Aviation, Wuxi; 214063, China |
Recommended Citation GB/T 7714 | Chen, Hua,Guo, Wei,Yan, Jing-Wen,et al. A new deep learning method for roads recognition from SAR images[J]. Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition),2020,50(5):1778-1787. |
APA | Chen, Hua,Guo, Wei,Yan, Jing-Wen,Zhuo, Wen-Hao,&Wu, Liang-Bin.(2020).A new deep learning method for roads recognition from SAR images.Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition),50(5),1778-1787. |
MLA | Chen, Hua,et al."A new deep learning method for roads recognition from SAR images".Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) 50.5(2020):1778-1787. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment