基于双池化注意力机制的高光谱图像分类算法  

Hyperspectral image classification based on double pool attention mechanism

作　　者：陈栋 李明[1] 李莉[2] 陈淑文 CHEN Dong;LI Ming;LI Li;CHEN Shuwen(College of Computer and Information Science,Chongqing Normal University,Chongqing 401331;College of Computer and Information Science,Southwest University,Chongqing 400715;School of Mathematical Sciences,Chongqing Normal University,Chongqing 401331)

机构地区：[1]重庆师范大学计算机与信息科学学院,重庆401331 [2]西南大学计算机与信息科学学院,重庆400715 [3]重庆师范大学数学科学学院,重庆401331

出　　处：《南京信息工程大学学报（自然科学版）》2023年第4期393-402,共10页Journal of Nanjing University of Information Science & Technology（Natural Science Edition）

基　　金：国家自然科学基金(61877051,61170192);重庆市科委重点项目(cstc2017zdcy-zd yf0366);重庆市教委项目(113143);重庆市研究生教改重点项目(yjg182022)。

摘　　要：为了提高高光谱图像在有限训练样本下的分类性能,提出了一种基于双池化注意力机制的高光谱图像分类网络(DPAMN).首先,采用三维卷积提取高光谱图像的空间和光谱浅层信息.其次,为了增强网络的特征提取能力,在DPAMN中引入了一种双池化注意力机制.最后,在网络的深层引入三维卷积密集连接模块,该模块不仅能够充分提取高光谱图像的空间和光谱特征,同时还能提高特征的判别能力.实验结果表明,在Indian Pines、University of Pavia、Salinas以及Houston 2013数据集上分别取得95.45%、97.11%、95.30%以及93.71%的整体平均精度,与目前主流的已有先进方法相比,所提出的方法在4个数据集上均有较大提升,表明所提方法具有较强的泛化能力.In order to improve the classification performance of hyperspectral images with limited training samples,a hyperspectral image classification Network based on Double Pooling Attention Mechanism(DPAMN)is proposed in this paper.First,the DPAMN uses three-dimensional convolution to extract the spatial and spectral shallow information of hyperspectral images.Second,the double pooling attention mechanism is introduced into DPAMN to enhance the feature extraction ability of the network.Finally,the three-dimensional convolution dense connection module is introduced into the deep layer of the network,which can not only fully extract the spatial and spectral features of hyperspectral images,but also improve the ability of feature discrimination.Experiments show that the overall average accuracy of 95.45%,97.11%,95.30%and 93.71%can be achieved on datasets of Indian Pines,University of Pavia,Salinas and Houston 2013,respectively.Compared with the current mainstream advanced methods,the proposed method greatly improves classification performance on four datasets,indicating its strong generalization capacity.

关 键 词：卷积神经网络 高光谱图像 分类 注意力机制 空谱特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]