结合协方差池化与跨尺度特征提取的高光谱分类  

Hyperspectral classification algorithm based on covariance pooling and cross scale feature extraction

作　　者：汪乐 彭江涛 陈娜[1] 孙伟伟 WANG Le;PENG Jiangtao;CHEN Na;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203-218,共16页NATIONAL REMOTE SENSING BULLETIN

基　　金：国家重点研发计划(编号:2020YFA0714200);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：深度卷积神经网络在高光谱图像分类任务上取得了优越性能。但是,主流深度学习算法通常采用一阶池化运算,容易忽略光谱之间的相关性,因而难以获取高阶统计判别特征。另外,这类算法往往难以选择最优的窗口大小去捕获不同感受野信息。针对上述问题,本文提出了一种结合协方差池化和跨尺度特征提取的高光谱影像分类方法。该方法设计了跨尺度自适应特征提取模块,能够自动提取多尺度特征,获取不同视野的互补信息,避免了尺度选择问题;进一步利用平均池化和快速协方差池化的联合池化操作,得到一阶统计量和结合空间光谱信息的二阶统计量;最终,将一阶和二阶池化特征进行融合用于分类。在3个公开高光谱数据集Indian Pines、Houston和Pavia University上分别随机选取5%、5%和1%标记样本进行训练,本文算法得到的总体分类精度分别达到97.63%、98.48%和98.21%,分类性能优于主流深度学习方法。The deep convolution neural network algorithm has achieved excellent performance in hyperspectral image classification.However,these deep learning algorithms generally use first-order pooling operation,which ignores the correlation between different spectral bands.Thus,obtaining high-order statistical discriminant features is difficult.In addition,using these algorithms to choose the optimal window size and capture different receptive field information is complicated.This paper proposes a hyperspectral classification method combining covariance pooling and cross-scale feature extraction to solve the aforementioned problems.This method aims to automatically extract the complementary and discriminative information of different scales and exploit the first-and second-order pooling features to improve the classification performance.A covariance pooling and cross-scale feature extraction method is proposed for hyperspectral image classification.In this method,a cross-scale adaptive feature extraction module is designed.This module can automatically combine multiscale feature information and obtain complementary information of different visual fields,avoiding the scale selection problem.Furthermore,the first-and second-order statistics combined with spatial-spectral information are obtained using the joint pooling operation of average and fast covariance pooling.Finally,the first-and second-order pooled features are fused for classification.A total of 5%,5%,and 1%labeled samples were randomly selected from three public hyperspectral datasets,namely,Indian pines,Houston University,and Pavia University,respectively.The overall classification accuracy of the proposed algorithm reached 97.63%,98.48%,and 98.21%,and the classification performance was better than the state-of-the-art deep learning methods.Cross-scale feature extraction considers the complementary spatial-spectral information between different scales to obtain additional adaptive feature information.Combining fast covariance and average pooling,the discriminan

关 键 词：高光谱图像分类 协方差池化 多尺度 特征融合 卷积神经网络 

分 类 号：P407.8[天文地球—大气科学及气象学] P2