A second-order attention network for glacial lake segmentation from remotely sensed imagery
A second-order attention network for glacial lake segmentation from remotely sensed imagery
复制标题
DOI：
10.1016/j.isprsjprs.2022.05.007
复制
发表时间：
2022-07
影响因子：
12.7
通讯作者：
Shidong Wang;M. Peppa;W. Xiao;S. B. Maharjan;S. Joshi;J. Mills
中科院分区：
文献类型：
--
作者：
Shidong Wang;M. Peppa;W. Xiao;S. B. Maharjan;S. Joshi;J. Mills
在世界上许多最脆弱的高山地区，气候变化正在增加冰湖溃决洪水（GLOFs）的风险。与此同时，遥感技术现在促进了对全球冰湖演变的持续监测，尽管从卫星数据中准确可靠地自动绘制冰湖地图仍然具有挑战性。在本研究中，设计了一种二阶注意力网络（SoAN），用于从卫星图像中自动分割湖泊。特别地，提出了一种新的二阶注意模块（SoAM）来捕获远程空间依赖性，并从局部特征的协方差表示中建立通道注意。此外，由于输入张量和输出张量的维度是相同的，并且它仅仅依赖于矩阵计算，因此所提出的SoAM可以嵌入到给定架构的不同位置，同时保持相似的参考速度。设计的网络在Landsat-8图像上实现，并与代表性深度学习模型的输出进行了比较，结果显示改进的结果，Dice为81.02%，F2分数为85.17%。
Climate change is increasing the risk of glacial lake outburst floods (GLOFs) in many of the world’s most vulnerable and high mountain regions. Simultaneously, remote sensing technologies now facilitate continuous monitoring of glacial lake evolution around the globe, although accurate and reliable automated glacial lake mapping from satellite data remains challenging. In this study, a Second-order Attention Network (SoAN) is devised for the automated segmentation of lakes from satellite imagery. In particular, a novel Second-order Attention Module (SoAM) is proposed to capture the long-range spatial dependencies and establish channel attention derived from the covariance representations of local features. Furthermore, as the dimensions of the input and output tensors are identical and it simply relies on matrix calculations, the proposed SoAM can be embedded into different positions of a given architecture while maintaining similar reference speed. The designed network is implemented on Landsat-8 imagery and outputs are compared against representative deep learning models, demonstrating improved results with a Dice of 81.02% and a F2 Score of 85.17%.