Author Affiliations
1Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China2University of Chinese Academy of Sciences, Beijing 100049, China3Urban and Rural Planning Management Center of the Ministry of Housing and Urban-Rural Development,Beijing 100835, Chinashow less
Fig. 1. Technical routes for extracting the water body
Fig. 2. U-Net architecture
Fig. 3. Improved U-Net network low-dimensional information enhancement
Fig. 4. Full connection condition random field post-processing model
Fig. 5. Location of Qingdao study area
Fig. 6. GF-2 image processing flowchart
Fig. 7. Training curve of improved U-Net
| 感受野 | 步长 | 填充 | 输出大小 |
---|
InputRGBimage:3@256×256 | Conv+ReLU | 3×3 | 1 | 1 | 64@256×256 | Conv+ReLU | 3×3 | 1 | 1 | 64@256×256 | Max-pooling | 64@128×128 | Conv+ReLU | 3×3 | 1 | 1 | 128@128×128 | Conv+ReLU | 3×3 | 1 | 1 | 128@128×128 | Max-pooling | 128@64×64 | Conv+ReLU | 3×3 | 1 | 1 | 256@64×64 | Conv+ReLU | 3×3 | 1 | 1 | 256@64×64 | Conv+ReLU | 3×3 | 1 | 1 | 256@64×64 | Max-pooling | 256@32×32 | Conv+ReLU | 3×3 | 1 | 1 | 512@32×32 | Conv+ReLU | 3×3 | 1 | 1 | 512@32×32 | Conv+ReLU | 3×3 | 1 | 1 | 512@32×32 | Max-pooling | 512@16×16 | Conv+ReLU | 3×3 | 1 | 1 | 512@16×16 | Conv+ReLU | 3×3 | 1 | 1 | 512@16×16 | Conv+ReLU | 3×3 | 1 | 1 | 512@16×16 | Max-pooling | 512@8×8 |
|
Table 1. VGG16 network structure configuration
影像编号 | 中心经度/°E | 中心纬度/°N | 成像时间 | 影像大小/像素×像素 |
---|
L1A0003593712 | 120.5 | 36.7 | 2018-11-12 | 27 620×35 273 | L1A0003593719 | 120.4 | 36.3 | 2018-11-12 | 27 620×35 113 | L1A0003593868 | 120.6 | 36.3 | 2018-11-12 | 27 620×35 191 |
|
Table 2. RemotesensingimageinformationintheQingdaostudyarea
项目 | 系统 | CPU | 内存 | 硬盘 | 显卡 |
---|
内容 | Ubuntu16.04 | Intel E5-1630 | 8 GB | 500 GB | NVIDIA GTX970 |
|
Table 3. Basic system platform configuration
项目 | GPU-Driver | CUDA | Python | Keras | Tensorflow-gpu |
---|
内容 | 384 | 8.0 | 3.6 | 2.2.4 | 1.4.0 |
|
Table 4. Important software configuration
Table 5. Comparison of water extraction results by different methods in 5 typical areas of the study area
Table 6. Confusion matrix for accuracy evaluation
方法 | IoU/% | 精准率/% | Kappa系数 |
---|
SegNet | 77.6 | 82.5 | 0.79 | 经典U-net | 82.3 | 90.4 | 0.88 | 改进后的U-Net网络 | 88.1 | 94.8 | 0.93 |
|
Table 7. Accuracy comparison of water extraction results
影像编号 | 中心经度/°E | 中心纬度/°N | 成像时间 | 影像大小/像素×像素 |
---|
L1A0003553729 | 120.1 | 36.3 | 2018-10-28 | 276 20×292 00 | L1A0003351642 | 101.5 | 36.8 | 2018-07-26 | 276 20×292 00 |
|
Table 8. Remote sensing image information in the application area
| | 区域1 | 区域2 | 区域3 | 区域4 | 区域5 |
---|
青岛 | 原始影像 | | | | | | | 水体信息 | | | | | | 西宁 | 原始影像 | | | | | | | 水体信息 | | | | | |
|
Table 9. Comparison of water extraction results in 5 typical areas of the application area