面向高光谱影像小样本分类的全局-局部特征自适应融合方法  

Global-local Feature Adaptive Fusion Method for Small Sample Classification of Hyperspectral Images

作　　者：左溪冰 刘智 金飞[1] 林雨准 王淑香 刘潇 李美霖 ZUO Xibing;LIU Zhi;JIN Fei;LIN Yuzhun;WANG Shuxiang;LIU Xiao;LI Meilin(Institute of Geospatial Information,Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学地理空间信息学院,郑州450001

出　　处：《地球信息科学学报》2023年第8期1699-1716,共18页Journal of Geo-information Science

基　　金：河南省自然科学基金项目(222300420387)。

摘　　要：高光谱影像标记样本的获取通常是一项费时费力的工作,如何在小样本条件下提高影像的分类精度是高光谱影像分类领域面临的难题之一。现有的高光谱影像分类方法对影像的多尺度信息挖掘不够充分,导致在小样本条件下的分类精度较差。针对此问题,本文设计了一种面向高光谱影像小样本分类的全局特征与局部特征自适应融合方法。该方法基于动态图卷积网络和深度可分离卷积网络,分别从全局尺度和局部尺度挖掘影像的潜在信息,实现了标记样本的有效利用。进一步引入极化自注意力机制,在减少信息损失的同时提升网络的特征表达,并采用特征自适应融合机制对全局特征和局部特征进行自适应融合。为验证本文方法的有效性,在University of Pavia、Salinas、WHU-Hi-LongKou和WHU-Hi-HanChuan4组高光谱影像基准数据集上开展分类试验。试验结果表明,与传统分类器和先进的深度学习模型相比,本文方法兼顾执行效率和分类精度,在小样本条件下能够取得更为优异的分类表现。在4组数据集上的总体分类精度分别为99.01%、99.42%、99.18%和95.84%,平均分类精度分别为99.31%、99.65%、98.89%和95.49%,Kappa系数分别为98.69%、99.35%、98.93%和95.14%。本文方法对应的代码开源于https://github.com/IceStreams/GLFAF。Acquisition of labeled samples for hyperspectral image classification is usually a time-and laborconsuming task.How to effectively improve the classification accuracy using a small number of samples is one of the challenges in the field of hyperspectral image classification.Most of existing classification methods for hyperspectral images lack sufficient multi-scale information mining,which leads to unsatisfactory classification performance due to small sample numbers.To address the aforementioned issue,this paper designed an adaptive fusion method by integrating global and local features for hyperspectral image classification with small sample numbers.Based on the dynamic graph convolutional network and the depth wise separable convolutional network,a two-branch network structure was constructed to mine the potential information of hyperspectral images from the global and local scales,which realizes the effective usage of labeled samples.Furthermore,the polarization self-attention mechanism was introduced to further improve the expression of intermediate features in the network while cutting down the loss of feature information,and the adaptive feature fusion mechanism was adopted to carry out adaptive fusion of global and local features.Finally,the fusion features flow into the full-connection layer and are manipulated by softmax to obtain prediction labels for each pixel of the hyperspectral image.In order to verify the effectiveness of the proposed method,classification experiments were carried out on four hyperspectral image benchmark data sets including University of Pavia,Salinas,WHU-Hi-LongKou,and WHU-Hi-HanChuan.We discussed and analyzed the influence of model parameters and different modules on the classification accuracy.Subsequently,a comprehensive comparison with seven existing advanced classification methods was conducted in terms of classification visualization,classification accuracy,number of labeled samples,and execution efficiency.The experimental results show that the dynamic graph convolutiona

关 键 词：高光谱影像分类 小样本 深度学习 深度可分离卷积网络 超像素分割 动态图卷积网络 极化自注意力机制 特征自适应融合 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]