基于卷积神经网络的高光谱图像分类算法综述  

A Survey of Hyperspectral Image Classification Algorithms Based on Convolutional Neural Networks

作　　者：易瑔 张宇航 宗艳桃 戴颜斌 YI Quan;ZHANG Yuhang;ZONG Yantao;DAI Yanbin(Department of Weaponry and Control,Army Academy of Armed Forces,Beijing 100000,China)

机构地区：[1]中国人民解放军陆军装甲兵学院兵器与控制系,北京100000

出　　处：《电光与控制》2023年第3期70-77,共8页Electronics Optics & Control

摘　　要：高光谱图像拥有光谱分辨率高、图谱合一的优点,已经成为遥感科学的重要研究方向。大多数传统的高光谱图像分类方法是基于浅层人工特征且依赖于专家经验,已经难以满足当下的技术需求。近年来,随着卷积神经网络在人工智能领域的广泛应用,基于卷积神经网络的高光谱图像分类方法已经在分类精度和速度上取得突破性的进展。首先介绍了高光谱图像分类方法,分析了传统分类方法的局限性;然后根据卷积神经网络对高光谱图像特征提取方式的不同,将算法分为基于谱特征、空间特征和空谱特征3大类,并分析了每类算法的优缺点;最后对高光谱图像分类的小样本训练、实际应用和分类结果等问题提出建议。Hyperspectral image has been considered as one of the greatest research directions in the remote sensing science due to its advantages of high spectral resolution as well as allowing for the synchronous acquisition of both images and spectra of objects.Most conventional hyperspectral image classification methods,however,are based on “shallow” handcrafted features,and highly relies on expert knowledge,which are difficult to meet the current technical requirements.In recent years,with the wide application of convolutional neural networks in the field of artificial intelligence,hyperspectral image classification methods based on convolutional neural networks have achieved breakthroughs in classification accuracy and speed.Firstly, hyperspectral image classification methods are introduced,and the limitations of traditional classification methods are analyzed.Secondly,according to the different extraction methods of hyperspectral image features by convolutional neural networks,the algorithm is divided into three types: Spectral features,spatial features and spatial-spectral features,and the merits and demerits are analyzed.Finally,some suggestions are put forward for the insufficient sample training,practical application and classification results of hyperspectral image classification.

关 键 词：高光谱图像 深度学习 图像分类 卷积神经网络 特征提取 综述 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]