机电工程技术2025，Vol.54Issue(21)：1-8,8.DOI:10.3969/j.issn.1009-9492.2025.21.001
基于卷积神经网络的遥感图像分类综述
Review on Remote Sensing Image Classification Based on Convolutional Neural Network
摘要
Abstract
As one of the representative algorithms of deep learning,convolutional neural network has shown excellent ability in remote sensing image classification tasks by virtue of its advantages in image feature extraction and pattern recognition,and has become a hot research direction in this field.Therefore,it is necessary to comprehensively review the important content of convolutional neural networks in remote sensing image classification tasks.Research progress of convolutional neural network in remote sensing image classification task is summarized,and the research status of remote sensing image classification is systematically sorted out.Widely used remote sensing image classification datasets are introduced and summarized.Then,the evaluation indexes commonly used in remote sensing image processing are described in detail,which provides a reference for the objective evaluation of the performance of convolutional neural network model.Main challenges and technical development trends of classes in remote sensing image classification tasks are summarized.This review aims to provide a comprehensive technical background and research direction for relevant researchers,and promote the further development and application of convolutional neural networks in remote sensing image classification tasks.关键词
卷积神经网络/遥感图像/分类/数据集/评价指标Key words
convolutional neural network/remote sensing images/classification/data set/evaluation index分类
计算机与自动化引用本文复制引用
夏文生,夏晓婧,邹金宝..基于卷积神经网络的遥感图像分类综述[J].机电工程技术,2025,54(21):1-8,8.基金项目
江西省教育厅科学技术研究项目(GJJ2403803) （GJJ2403803）
赣东学院院长基金(12224000613) （12224000613）
