Spatial-Pooling-Based Graph Attention U-Net for Hyperspectral Image Classification

Author:

Diao Qi1,Dai Yaping1ORCID,Wang Jiacheng1,Feng Xiaoxue1,Pan Feng1,Zhang Ce2ORCID

Affiliation:

1. School of Automation, Beijing Institute of Technology, Beijing 100081, China

2. School of Geographical Sciences, University of Bristol, Bristol BS8 1SS, UK

Abstract

In recent years, graph convolutional networks (GCNs) have attracted increasing attention in hyperspectral image (HSI) classification owing to their exceptional representation capabilities. However, the high computational requirements of GCNs have led most existing GCN-based HSI classification methods to utilize superpixels as graph nodes, thereby limiting the spatial topology scale and neglecting pixel-level spectral–spatial features. To address these limitations, we propose a novel HSI classification network based on graph convolution called the spatial-pooling-based graph attention U-net (SPGAU). Specifically, unlike existing GCN models that rely on fixed graphs, our model involves a spatial pooling method that emulates the region-growing process of superpixels and constructs multi-level graphs by progressively merging adjacent graph nodes. Inspired by the CNN classification framework U-net, SPGAU’s model has a U-shaped structure, realizing multi-scale feature extraction from coarse to fine and gradually fusing features from different graph levels. Additionally, the proposed graph attention convolution method adaptively aggregates adjacency information, thereby further enhancing feature extraction efficiency. Moreover, a 1D-CNN is established to extract pixel-level features, striking an optimal balance between enhancing the feature quality and reducing the computational burden. Experimental results on three representative benchmark datasets demonstrate that the proposed SPGAU outperforms other mainstream models both qualitatively and quantitatively.

Funder

National Natural Science Foundation of China

Technical Field Foundation of the National Defense Science and Technology 173 Program

Publisher

MDPI AG

Reference66 articles.

1. Graph neural network via edge convolution for hyperspectral image classification;Hu;IEEE Geosci. Remote Sens. Lett.,2021

2. Spectral-spatial feature tokenization transformer for hyperspectral image classification;Sun;IEEE Trans. Geosci. Remote Sens.,2022

3. Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning;Ma;ISPRS J. Photogramm. Remote Sens.,2016

4. Enhanced mangrove vegetation index based on hyperspectral images for mapping mangrove;Yang;ISPRS J. Photogramm. Remote Sens.,2022

5. Hyper spectral image classifications for monitoring harvests in agriculture using fly optimization algorithm;Shitharth;Comput. Electr. Eng.,2022

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3