基于CNN的高分遥感影像深度语义特征提取研究综述

近年来,深度学习作为计算机视觉的研究热点,在诸多方面得以发展与应用。特征提取是理解和分析高分遥感影像的关键基础。为促进高分遥感影像特征提取技术的发展,总结了深度学习模型在高分遥感影像特征提取技术的研究与发展,如:AlexNet,VGG-网和GoogleNet等卷积网络模型在深度语义特征提取中的应用。此外,重点分析和讨论了以卷积神经网络模型为基础的各类深度学习模型在高分遥感影像特征提取方面的应用与创新,如:迁移学习的应用;卷积神经网络(Convolutional Neural Network,CNN)模型结构的改变;CNN模型与其他模型结构的结合等方式,均提升了深度语义特征提取能力。最后,对卷积神经网络模型在高分遥感影像深度语义特征提取方面存在的问题以及后续可能的研究趋势进行了分析。

A Survey of Depth Semantic Feature Extraction of High-Resolution Remote Sensing Images based on CNN

In recent years，deep learning has been developed and applied in many aspects as a research hotspot of computer vision.Feature extraction is the key basis for understanding and analyzing high-resolution remote sensing images.In order to promote the development of high-resolution remote sensing image feature extraction technology，the research and development of deep learning model in high-resolution remote sensing image feature extraction technology，such as：AlexNet，VGG-net，and GoogleNet convolutional network models，have been summarized in depth semantic features.In addition，the application of extraction is also focused on the application and innovation of various deep learning models based on convolutional neural network models in high-resolution remote sensing image feature extraction，such as：application of migration learning；The combination of the CNN model and other model structures enhances the ability to extract deep semantic features.Finally，the problems of the convolutional neural network model in the extraction of deep semantic features of high-resolution remote sensing images and the possible research trends are analyzed.