基于加权特征融合的多尺度遥感影像分类  

Multi-scale Remote Sensing Image Classification Based on Weighted Feature Fusion

作　　者：程寅翥 刘松 王楠 师悦天 张耿[1] CHENG Yinzhu;LIU Song;WANG Nan;SHI Yuetian;ZHANG Geng(Xi'an Institute of Optics and Precision Mechanics,Chinese Academy of Sciences,Xi'an 710119,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院西安光学精密机械研究所光谱成像技术重点实验室,西安710119 [2]中国科学院大学,北京100049

出　　处：《光子学报》2023年第11期263-277,共15页Acta Photonica Sinica

基　　金：基础加强计划重点项目(No.2022-JCJQ-ZD-215-03);自主部署项目(No.S22-037)。

摘　　要：针对普通的三维卷积神经网络(3D CNN)从一个尺度上提取特征,会丢失部分细节信息,且对小样本任务表现一般的问题,本文提出了一种三支路的3D CNN,从不同尺度上提取特征后进行加权特征融合,从而获取了更为全面的特征;并引入数据增强技术,从而改善了小样本情形下的分类性能。现有特征融合方法通常对各个支路直接进行拼接,本文采用加权拼接的特征融合方法,将各特征分别乘以一个加权系数后再进行拼接,该系数通过模拟退火算法求取。本文方法在公开数据集Indian Pines,Pavia University,Salinas等上采用10%的数据进行训练,分别得到了98.60%、99.83%、99.97%的总体准确率,与各类对比方法相比,提升了高光谱遥感影像分类问题的准确率。Remote sensing image classification is a key branch in remote sensing image processing,which provides an important basis for agricultural,industrial,and military applications.With the development of remote sensing satellite,spectral imaging technique has also developed from multi-spectral technology to hyperspectral technology.Rich spectral information puts forward higher requirements for remote sensing image classification.Many hyperspectral image classification algorithms based on traditional methods,such as superpixel methods,extended morphological feature methods,space-spectral joint classification algorithms based on combined kernels,and classification algorithms based on support vector machines and graph cuts,have achieved certain results.In recent years,benefiting from the improvement of hardware conditions and the update and iteration of algorithms,various deep learning methods have emerged one after another,and have been introduced into the field of hyperspectral image classification by researchers,further improving the accuracy of hyperspectral classification.Autoencoder,Convolutional Neural Network(CNN),and capsule neural network have all been experimentally verified to be effective in this field.Different from the common two-dimensional convolutional neural network,the convolution kernel of the three-dimensional convolutional neural network(3D CNN)is a cube,which can naturally integrate the features of spatial dimension and spectral dimension,and has achieved state-of-the-art performance in the field of remote sensing image classification.Conventional 3D CNN usually extracts data cube features from a single scale,which often loses certain local information;excessively increasing the depth of the model will lead to overfitting problems;limited by actual conditions,it is often difficult to obtain hyperspectral data with a large number of labels,while conventional 3D CNN does not perform well for few-sample situations(for example,the total sample size is only a few hundred).To solve these problems,a mult

关 键 词：光学遥感影像 深度学习 图像分类 卷积神经网络 特征融合 多尺度 

分 类 号：P407.8[天文地球—大气科学及气象学]