%0 Journal Article
%T 深度神经网络在遥感图像分析中的应用研究
Research on the Application of Deep Neural Network in Remote Sensing Image Analysis
%A 郭进
%A 刘超
%A 白颖奇
%J Geomatics Science and Technology
%P 99-108
%@ 2329-7239
%D 2025
%I Hans Publishing
%R 10.12677/gst.2025.132013
%X 随着遥感技术飞速发展，高分辨率遥感图像已成为环境监测、城市规划、农业管理等多个领域的重要手段。然而遥感图像数据量庞大且复杂，传统分析方法在处理大规模数据时面临计算效率低下和特征提取依赖人工设计等诸多挑战。近年来，深度神经网络(Deep Neural Networks, DNNs)，凭借强大的自动特征提取和模式识别能力，在遥感图像分析中展现出卓越的性能。本研究系统地综述了深度神经网络在遥感图像分类、目标检测、语义分割和变化检测等关键任务中的应用，分析了国内外在该领域的研究现状与进展。此外，本研究还探讨了多模态数据融合、模型轻量化与实时性优化、以及深度学习模型的可解释性等前沿研究方向。
With the rapid development of remote sensing technology, high-resolution remote sensing images have become an important means in multiple fields such as environmental monitoring, urban planning, and agricultural management. However, the volume and complexity of remote sensing image data pose significant challenges for traditional analysis methods, including low computational efficiency and the reliance on manual feature design for feature extraction when dealing with large-scale data. In recent years, deep neural networks (DNNs), with their powerful capabilities in automatic feature extraction and pattern recognition, have demonstrated outstanding performance in remote sensing image analysis. This study systematically reviews the application of deep neural networks in key tasks such as remote sensing image classification, object detection, semantic segmentation, and change detection, and analyzes the current research status and progress both domestically and internationally in this field. Additionally, this study also explores cutting-edge research directions such as multi-modal data fusion, model lightweighting and real-time optimization, as well as the interpretability of deep learning models.
%K 遥感影像，
%K 深度学习，
%K 神经网络，
%K 多模态数据融合，
%K 模型轻量化，
%K 模型的可解释性
Remote Sensing Imagery
%K Deep Learning
%K Neural Networks
%K Multimodal Data Fusion
%K Model Lightweight
%K Model Interpretability
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=113238