基于图卷积网络的多标签遥感图像分类  

Multi-label remote sensing image classification based on graph convolutional network

作　　者：杨敏航 陈龙 刘慧[1,3,4] 钱育蓉 Yang Minhang;Chen Long;Liu Hui;Qian Yurong(Key Laboratory of Signal Detection&Processing,Xinjiang Uygur Autonomous Region,Urumqi 830046,China;a.College of Software,Xinjiang University,Urumqi 830000,China;College of Information Science&Engineering,Xinjiang University,Urumqi 830000,China;Key Laboratory of Software Engineering,Xinjiang University,Urumqi 830000,China)

机构地区：[1]新疆维吾尔自治区信号检测与处理重点实验室,乌鲁木齐830046 [2]新疆大学软件学院,乌鲁木齐830000 [3]新疆大学软件工程重点实验室,乌鲁木齐830000 [4]新疆大学信息工程学院,乌鲁木齐830000

出　　处：《计算机应用研究》2021年第11期3439-3445,共7页Application Research of Computers

基　　金：国家自然科学基金资助项目(61966035);智能多模态信息处理团队资助项目(XJEDU2017T002)。

摘　　要：由于遥感图像包含物体类别多样,单个语义类别标签无法全面地描述图像内容,而多标签图像分类任务更加具有挑战性。通过探索深度图卷积网络(GCN),解决了多标签遥感图像分类缺乏对标签语义信息相关性利用的问题,提出了一种新的基于图卷积的多标签遥感图像分类网络,它包含图像特征学习模块、基于图卷积网络的分类器学习模块和图像特征差异化模块三个部分。在公开多标签遥感数据集Planet和UCM上与相关模型进行对比,在多标签遥感图像分类任务上可以得到了较好的分类结果。该方法使用图卷积等模块将多标签图像分类方法应用到遥感领域,提高了模型分类能力,缩短了模型训练时间。A single semantic category label cannot describe comprehensively the image content because remote sensing images contain various object categories.The task of multi-label image classification is more challenging.By exploring the depth graph convolutional network(GCN),this paper made up for the lack of relevance of label semantic information in multi-label remote sensing image classification,proposed a new multi-label remote sensing image classification network,multi-label remote sen-sing image classification network based on the GCN.It contained three parts:image feature learning module,classifiers lear-ning module based on GCN,and image feature differentiating module.Compared with the related models on the public multi label remote sensing datasets planet and UCM,the method can get better classification results on the multi label remote sensing image classification task.The method used modules such as graph convolution to apply multi-label image classification methods to remote sensing,which improved the model classification ability and shortened the model training time.

关 键 词：卷积神经网络 图卷积网络 多标签 遥感图像分类 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]