西华大学学报（自然科学版）2017，Vol.36Issue(4)：13-20,8.DOI:10.3969/j.issn.1673-159X.2017.04.003
基于深度卷积神经网络的高光谱遥感图像分类
Hyperspectral Remote Sensing Images Classification Using a Deep Convolutional Neural Network Model
摘要
Abstract
The traditional hyperspectral image classification model only considers the spectral feature information,and ignores the important role of image spatial structure information in classification.In order to improve the classification accuracy of hyperspectral remote sensing image,this paper present a deep learning model utilizing the rich spectral and spatial information in hyperspectral images for land cover classification application.The proposed model is able to automatically extract more abstract high-level features from the low-level features for classification.In addition,the network structure is highly invariant to translation,scaling and other forms of distortion.Experiment results show that the deep learning method can provide high performances in hyperspectral image classification applications.The feasibility and effectiveness of the deep convolution neural network for classification of hyperspectral images are verified.关键词
高光谱遥感图像/卷积神经网络/特征提取/logistic回归分类器/分类精度/可行性/有效性Key words
hyperspectral remote sensing image/deep convolutional neural network/feature extraction/logistic regression classifier/classification accuracy/feasibility/effectiveness分类
信息技术与安全科学引用本文复制引用
罗建华,李明奇,郑泽忠,李江..基于深度卷积神经网络的高光谱遥感图像分类[J].西华大学学报（自然科学版）,2017,36(4):13-20,8.基金项目
水资源与水电工程科学国家重点实验室开放基金资助项目(2014SWG04) （2014SWG04）
国土资源部地学空间信息技术重点实验室开放基金(KLGSIT201411) （KLGSIT201411）
广西空间信息与测绘重点实验室开放基金(140452413、GKN120711516). （140452413、GKN120711516）
