高光谱影像三分支分组空谱注意力深度分类网络  

Hyperspectral image classification based on three branch network with grouped spatial-spectral attention

作　　者：苏涵 陈娜 彭江涛 孙伟伟[2,3] SU Han;CHEN Na;PENG Jiangtao;SUN Weiwei(Hubei Key Laboratory of Applied Mathematics,Faculty of Mathematics and Statistics,Hubei University,Wuhan 430062,China;Department of Geography and Spatial Information Techniques,Ningbo University,Ningbo 315211,China;Industrial Research Institute of Remote Sensing,Ningbo University,Shiye Intelligent Technology Co.,Ltd,Ningbo 315211,China)

机构地区：[1]湖北大学数学与统计学学院应用数学湖北省重点实验室,武汉430062 [2]宁波大学地理与空间信息技术系,宁波315211 [3]宁波大学遥感遥测产业技术研究院,宁波拾烨智能科技有限公司,宁波315211

出　　处：《遥感学报》2024年第1期247-265,共19页NATIONAL REMOTE SENSING BULLETIN

基　　金：湖北省自然科学基金(编号:2021CFA087);国家自然科学基金(编号:42171351,42122009);浙江省“尖兵”“领雁”研发攻关计划(编号:2023C01027)。

摘　　要：高光谱影像具有丰富的空间和光谱信息,充分提取和利用这两个维度的信息是高光谱分类算法重点关注的问题。目前深度特征提取网络通常利用单分支串行网络连续提取空谱特征或双分支并行网络分别提取空谱特征。由于空间和光谱维内在差异,单分支串行网络连续提取的两类特征之间会互相干扰。并行双分支网络虽然可以减少两类特征之间的干扰,但同时会忽略空间和光谱特征间的潜在相关性。为解决上述问题,本文提出了一种三分支分组空谱注意力深度网络结构。该网络具有3个分支,分别用于提取空间、光谱和空谱联合特征。针对3个分支的不同特性,设计了不同的注意力机制以加强特征的判别性。该网络既可以提取独立的空间和光谱特征,又保留了空间和光谱之间的相关性。在5个数据集上的实验表明,本文所提出的方法要优于现有的一些先进算法。Hyperspectral images have abundant spatial and spectral information.Numerous hyperspectral classification algorithms focus on the extraction and maximization of spatial and spectral information.Deep feature extraction networks generally extract spectral-spatial features using single-branch serial or double-branch parallel structures.However,single-branch structures may lead to mutual interference between features of spectral and spatial dimensions,and double-branch parallel structures tend to ignore the correlation between spatial and spectral features.This paper proposes a three-branch grouped spatial-spectral attention network(TGSSAN)to consider the differences and correlations between spatial and spectral features.TGSSAN can extract independent spectral-spatial features while preserving their correlation.This paper proposes the TGSSAN,which has three parallel branches(i.e.,spectral,spatial,and spectral-spatial branches).These branches can separately extract spectral,spatial,and spatial-spectral features.Different attention blocks are designed in three branches to enhance the discriminative capability of features.In particular,a grouped spatial-spectral attention mechanism is proposed in the spectralspatial branch to obtain spatial and spectral attention simultaneously.Finally,three branch features are fused for classification.In the experiment,the proposed TGSSAN algorithm is compared with some advanced deep learning algorithms,such as SSRN,FDSSC,DBMA,DBDA,HResNetAM,and A2S2KResNet.The performance of different algorithms is evaluated on five hyperspectral data sets.Experimental results show that the proposed algorithm achieved superior classification performance on IP,PU,SA,HU,and HHK datasets.In particular,the proposed algorithm achieves higher classification accuracy despite limited training samples compared with the existing advanced algorithms.The TGSSAN method proposed in this paper improves the shortcomings of the single-branch serial and double-branch parallel structures for continuous extraction of spe

关 键 词：高光谱影像分类 注意力机制 三分支结构 深度网络 

分 类 号：TP701[自动化与计算机技术—检测技术与自动化装置] P2[自动化与计算机技术—控制科学与工程]