Deep Convolutional Neural Networks for Hyperspectral Image Classification

Deep Convolutional Neural Networks for Hyperspectral Image Classification

Recently, convolutional neural networks have demonstrated excellent performance on various visual tasks, including the classification of common two-dimensional images. In this paper, deep convolutional neural networks are employed to classify hyperspectral images directly in spectral domain. More sp...

Full description

Bibliographic Details
Main Authors: Wei Hu, Yangyu Huang, Li Wei, Fan Zhang, Hengchao Li
Format: Article
Language:English
Published: Hindawi Limited 2015-01-01
Series:Journal of Sensors
Online Access:http://dx.doi.org/10.1155/2015/258619
id doaj-ad36fc8664884fa49fa8e23dccf2ed72
record_format Article
spelling doaj-ad36fc8664884fa49fa8e23dccf2ed722020-11-24T22:34:30ZengHindawi LimitedJournal of Sensors1687-725X1687-72682015-01-01201510.1155/2015/258619258619Deep Convolutional Neural Networks for Hyperspectral Image ClassificationWei Hu0Yangyu Huang1Li Wei2Fan Zhang3Hengchao Li4College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 10029, ChinaCollege of Information Science and Technology, Beijing University of Chemical Technology, Beijing 10029, ChinaCollege of Information Science and Technology, Beijing University of Chemical Technology, Beijing 10029, ChinaCollege of Information Science and Technology, Beijing University of Chemical Technology, Beijing 10029, ChinaSichuan Provincial Key Laboratory of Information Coding and Transmission, Southwest Jiaotong University, Chengdu 610031, ChinaRecently, convolutional neural networks have demonstrated excellent performance on various visual tasks, including the classification of common two-dimensional images. In this paper, deep convolutional neural networks are employed to classify hyperspectral images directly in spectral domain. More specifically, the architecture of the proposed classifier contains five layers with weights which are the input layer, the convolutional layer, the max pooling layer, the full connection layer, and the output layer. These five layers are implemented on each spectral signature to discriminate against others. Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than some traditional methods, such as support vector machines and the conventional deep learning-based methods.http://dx.doi.org/10.1155/2015/258619
collection DOAJ
language English
format Article
sources DOAJ
author Wei Hu
Yangyu Huang
Li Wei
Fan Zhang
Hengchao Li
spellingShingle Wei Hu
Yangyu Huang
Li Wei
Fan Zhang
Hengchao Li
Deep Convolutional Neural Networks for Hyperspectral Image Classification
Journal of Sensors
author_facet Wei Hu
Yangyu Huang
Li Wei
Fan Zhang
Hengchao Li
author_sort Wei Hu
title Deep Convolutional Neural Networks for Hyperspectral Image Classification
title_short Deep Convolutional Neural Networks for Hyperspectral Image Classification
title_full Deep Convolutional Neural Networks for Hyperspectral Image Classification
title_fullStr Deep Convolutional Neural Networks for Hyperspectral Image Classification
title_full_unstemmed Deep Convolutional Neural Networks for Hyperspectral Image Classification
title_sort deep convolutional neural networks for hyperspectral image classification
publisher Hindawi Limited
series Journal of Sensors
issn 1687-725X
1687-7268
publishDate 2015-01-01
description Recently, convolutional neural networks have demonstrated excellent performance on various visual tasks, including the classification of common two-dimensional images. In this paper, deep convolutional neural networks are employed to classify hyperspectral images directly in spectral domain. More specifically, the architecture of the proposed classifier contains five layers with weights which are the input layer, the convolutional layer, the max pooling layer, the full connection layer, and the output layer. These five layers are implemented on each spectral signature to discriminate against others. Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than some traditional methods, such as support vector machines and the conventional deep learning-based methods.
url http://dx.doi.org/10.1155/2015/258619
work_keys_str_mv AT weihu deepconvolutionalneuralnetworksforhyperspectralimageclassification
AT yangyuhuang deepconvolutionalneuralnetworksforhyperspectralimageclassification
AT liwei deepconvolutionalneuralnetworksforhyperspectralimageclassification
AT fanzhang deepconvolutionalneuralnetworksforhyperspectralimageclassification
AT hengchaoli deepconvolutionalneuralnetworksforhyperspectralimageclassification
_version_ 1725727127531159552

Similar Items