Paper Info
Title
Multilayer Global Spectral-Spatial Attention Network for Wetland Hyperspectral Image Classification
Abstract
Coastal wetland monitoring plays an important role in the protection and restoration of ecosystems in this world. UAV-hyperspectral imaging, as an emerging technique for Earth observation and space exploration, provides the huge potential ability to identify different wetland species. In this work, a multilayer global spectral-spatial attention network (MGSSAN) is proposed for mapping coastal wetlands, which mainly consists of two major steps. First, a two-branch convolutional neural network (CNN) framework with residual connection is developed to obtain an initial classification probability map, in which one branch is used to capture the spectral information, the other branch is used to extract spatial information, and a global spectral-spatial attention module is designed to guide networks focusing on those features that are more discriminative. Second, an extended random walker method is utilized to optimize the initial classification probabilities, so as to yield the final map. Experiments performed on three wetland HSI datasets created by ourselves verify that the proposed method can obtain superior performance with respect to several state-of-the-art hyperspectral image classification methods.
Year
DOI
Venue
2022
10.1109/TGRS.2021.3133454
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Keywords
DocType
Volume
Feature extraction, Wetlands, Hyperspectral imaging, Sea measurements, Data mining, Autonomous aerial vehicles, Data visualization, Deep learning, extended random walk, global spectral-spatial attention (GSSA), hyperspectral image classification, residual connection
Journal
60
ISSN
Citations 
PageRank 
0196-2892
0
0.34
References 
Authors
0
5
Name
Order
Citations
PageRank
Zhuojun Xie100.34
Jianwen Hu201.01
Xudong Kang345122.68
Puhong Duan400.68
Shutao Li52594139.10