Spacecraft Recovery & Remote Sensing, Volume. 45, Issue 6, 124(2024)
Multi-scale Attention Network for High-Precision Automatic Detection of Water Bodies in SAR Images
Figures & Tables(13)
![[in Chinese]](/Images/icon/loading.gif){kind=icon}
Table 1. Water body extraction metrics for SAR images by different networks
View tableView in ArticleTable 1. Water body extraction metrics for SAR images by different networks
模型 场景 P/% I/% R/% F1/% 训练时间/h UNet Ⅰ Ⅱ 80.63 80.40 76.22 71.15 93.30 90.97 86.51 81.34 13.25 LinkNet Ⅰ Ⅱ 83.92 81.42 77.48 72.06 92.03 90.12 89.77 82.65 8.50 BuildFormer Ⅰ Ⅱ 85.15 81.79 78.90 72.19 91.49 90.87 88.21 82.99 12.33 MATLinkNet Ⅰ Ⅱ 90.73 86.69 81.95 75.66 89.69 82.68 90.98 83.94 9.20
Table 2. Comparison of ablation results
View tableView in ArticleTable 2. Comparison of ablation results
网络模型 场景 P/% I/% 原始LinkNet Ⅰ Ⅱ 83.92 81.42 77.48 72.06 原始LinkNet+3个3×3卷积 Ⅰ 87.19 80.09 Ⅱ 83.32 73.26 原始LinkNet+AMSP Ⅰ 86.76 78.89 Ⅱ 84.59 74.46 本文方法（MATLinkNet） Ⅰ 90.73 81.95 Ⅱ 86.69 75.66
Tools
Get Citation
Copy Citation Text
Xiujuan LIANG, Hongguang XIAO, Lifu CHEN, Xiqian FAN. Multi-scale Attention Network for High-Precision Automatic Detection of Water Bodies in SAR Images[J]. Spacecraft Recovery & Remote Sensing, 2024, 45(6): 124
Paper Information
Category:
Received: Jan. 22, 2024
Accepted: --
Published Online: Jan. 23, 2025
The Author Email: FAN Xiqian (fanxiqian22@mails.ucas.ac.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20