融合字典学习与视觉转换器的高分遥感影像场景分类方法  

Classification Method of High-Resolution Remote Sensing Scene Image Based on Dictionary Learning and Vision Transformer

作　　者：何晓军 刘璇 魏宪 He Xiaojun;Liu Xuan;Wei Xian(College of Software,Liaoning Technical University,Huludao 125105,Liaoning,China;Quanzhou Institute of Equipment Manufacturing Haixi Institutes,Fujian Institute of Research on the Structure,Chinese Academy of Sciences,Quanzhou 362216,Fujian,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125105 [2]中国科学院福建物质结构研究所泉州装备制造研究中心,福建泉州362216

出　　处：《激光与光电子学进展》2023年第14期181-190,共10页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(41801368);辽宁省教育厅科学研究项目(LJKZ0350);辽宁省教育厅重点项目(LJ2020ZD003);福建省科技计划项目(2021T3003,2021T3068);泉州市科技计划项目(2021C065L)。

摘　　要：遥感影像场景分类方法多基于传统机器学习或卷积神经网络,此类方法的特征提取能力极为有限,尤其在处理类间相似度大、空间信息复杂、几何结构繁多的光学遥感影像时更容易出现特征信息丢失、分类精度受限等问题。基于此,提出一种融合字典学习与视觉转换器(ViT)的高分辨率遥感影像场景分类方法。该方法不仅能够挖掘图像内部的长距离依赖关系,而且可以利用字典学习抓取图像的深层非线性结构信息,从而达到提升分类准确度的目的。在PyTorch深度学习框架上,在RSSCN7、NWPU-RESISC45和Aerial Image Data Set(AID)3个公开的遥感影像数据集上对所提方法和模型进行了广泛实验,验证了所提方法的可行性,其分类正确率比原始视觉转换器模型分别高出1.763个百分点、1.321个百分点和3.704个百分点。与其他先进的场景分类方法相比,所提方法实现了更加优异的分类性能。Classification methods of remote sensing scene images are mostly based on traditional machine learning or convolutional neural networks.The feature extraction capability of such methods is extremely limited,particularly for optical remote sensing images with large interclass similarity,complex spatial information,and various geometric structures,there are problems such as loss of feature information and low classification accuracy.To overcome these problems,we propose a high-resolution remote sensing scene image classification method that combines dictionary learning and Vision Transformer(ViT).This method can not only mine the long-distance dependencies inside the images but can also use dictionary learning to capture the deep nonlinear structural information of images to improve classification accuracy.Through extensive experiments performed on the RSSCN7,NWPU-RESISC45,and Aerial Image Data Set(AID)public remote sensing image datasets trained from scratch on the PyTorch deep learning framework,the effectiveness of the proposed method is verified;the results show that the classification accuracy of the proposed method for the mentioned datasets is 1.763 percentage points,1.321 percentage points,and 3.704 percentage points higher than that of the original visual converter model,respectively.Moreover,the proposed method outperforms other advanced scene classification methods.

关 键 词：视觉转换器 字典学习 遥感场景分类 高分辨率遥感影像 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]