Automatic Extraction of Water and Shadow from SAR Images Based on a Multi-Resolution Dense Encoder and Decoder Network
Automatic Extraction of Water and Shadow from SAR Images Based on a Multi-Resolution Dense Encoder and Decoder Network
复制标题
基于多分辨率密集编码器和解码器网络的SAR图像水和阴影自动提取
DOI：
10.3390/s19163576
复制
发表时间：
2019-08
期刊：
影响因子：
3.9
通讯作者：
Yuan Zhihui
中科院分区：
文献类型：
--
作者：
Zhang Peng;Chen Lifu;Li Zhenhong;Xing Jin;Xing Xuemin;Yuan Zhihui
SAR图像中的水体和阴影区域包含着丰富的应用信息，目前还不能自动精确地提取。为了解决这个问题，提出了一种称为多分辨率密集编码器和解码器（MRDED）网络的新框架，它集成了卷积神经网络（CNN），残差网络（ResNet），密集卷积网络（DenseNet），全局卷积网络（GCN）和卷积长短期记忆（ConvLSTM）。MRDED包含三个部分：灰度梯度共生矩阵（GLGCM），编码器网络和解码器网络。GLGCM用于提取低级特征，这些特征由编码器进一步处理。Encoder网络使用ResNet来提取不同分辨率的特征。解码器网络有两个组成部分，即多级特征提取和融合（MFEF）和分数图融合（SF）。我们实现了两个版本的MFEF，命名为MFEF1和MFEF2，生成单独的分数图。它们之间的区别在于，MFEF 2中使用了链式残差池（CRP）模块，而MFEF 1中采用了ConvLSTM，形成了改进的链式残差池（ICRP）模块作为替代。由MFEF 1和MFEF 2生成的两个单独的分数图以不同的权重融合以产生融合的分数图，该融合的分数图由Softmax函数进一步处理以生成水和阴影区域的最终提取结果。为了评估所提出的框架，MRDED的训练和测试与大型SAR图像。为了进一步评估的分类性能，共八个不同的分类框架与我们提出的框架进行了比较。MRDED表现出色，对于水，像素准确度（PA）达到80.12%，联合交叉点（IoU）达到73.88%，对于阴影，PA达到88%，IoU达到77.11%，对于背景分类，PA达到95.16%，IoU达到90.49%。
The water and shadow areas in SAR images contain rich information for various applications, which cannot be extracted automatically and precisely at present. To handle this problem, a new framework called Multi-Resolution Dense Encoder and Decoder (MRDED) network is proposed, which integrates Convolutional Neural Network (CNN), Residual Network (ResNet), Dense Convolutional Network (DenseNet), Global Convolutional Network (GCN), and Convolutional Long Short-Term Memory (ConvLSTM). MRDED contains three parts: the Gray Level Gradient Co-occurrence Matrix (GLGCM), the Encoder network, and the Decoder network. GLGCM is used to extract low-level features, which are further processed by the Encoder. The Encoder network employs ResNet to extract features at different resolutions. There are two components of the Decoder network, namely, the Multi-level Features Extraction and Fusion (MFEF) and Score maps Fusion (SF). We implement two versions of MFEF, named MFEF1 and MFEF2, which generate separate score maps. The difference between them lies in that the Chained Residual Pooling (CRP) module is utilized in MFEF2, while ConvLSTM is adopted in MFEF1 to form the Improved Chained Residual Pooling (ICRP) module as the replacement. The two separate score maps generated by MFEF1 and MFEF2 are fused with different weights to produce the fused score map, which is further handled by the Softmax function to generate the final extraction results for water and shadow areas. To evaluate the proposed framework, MRDED is trained and tested with large SAR images. To further assess the classification performance, a total of eight different classification frameworks are compared with our proposed framework. MRDED outperformed by reaching 80.12% in Pixel Accuracy (PA) and 73.88% in Intersection of Union (IoU) for water, 88% in PA and 77.11% in IoU for shadow, and 95.16% in PA and 90.49% in IoU for background classification, respectively.
登录
查看更多内容
DOI：
10.3390/s150306652
发表时间：
2015-03-19
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Hong S;Jang H;Kim N;Sohn HG
通讯作者：
Sohn HG
影响因子：
8.2
作者：
Pasquale Iervolino;R. Guida;A. Iodice;D. Riccio
通讯作者：
Pasquale Iervolino;R. Guida;A. Iodice;D. Riccio
DOI：
10.1109/cvprw.2018.00048
发表时间：
2018-06
期刊：
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
影响因子：
--
作者：
A. Rakhlin;A. Davydow;S. Nikolenko
通讯作者：
A. Rakhlin;A. Davydow;S. Nikolenko
DOI：
10.4018/978-1-7998-1192-3.ch008
发表时间：
2020
期刊：
Advances in Systems Analysis, Software Engineering, and High Performance Computing
影响因子：
--
作者：
Menaga D.;R. S.
通讯作者：
Menaga D.;R. S.
DOI：
10.4018/978-1-5225-9096-5.ch007
发表时间：
2021-07
期刊：
Smart Computational Intelligence in Biomedical and Health Informatics
影响因子：
--
作者：
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi
通讯作者：
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi