Convolution Neural Network Based on Two-Dimensional Spectrum for Hyperspectral Image Classification

Inherent spectral characteristics of hyperspectral image (HSI) data are determined and need to be deeply mined. A convolution neural network (CNN) model of two-dimensional spectrum (2D spectrum) is proposed based on the advantages of deep learning to extract feature and classify HSI. First of all, t...

Full description

Saved in:
Bibliographic Details
Published in:Journal of sensors Vol. 2018; no. 2018; pp. 1 - 13
Main Authors: Li, Chenming, Yang, Yao, Lin, Shuo, Gao, Hongmin, Yang, Mingxiang
Format: Journal Article
Language:English
Published: Cairo, Egypt Hindawi Publishing Corporation 01.01.2018
Hindawi
John Wiley & Sons, Inc
Subjects:
Accuracy
Algorithms
Classification
Convolution
Data processing
Earth science
Feature extraction
Hyperspectral imaging
Image classification
Machine learning
Model accuracy
Neural networks
Performance enhancement
Principal components analysis
Remote sensing
Researchers
Spatial data
Spectra
Two dimensional models
ISSN:1687-725X, 1687-7268
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Inherent spectral characteristics of hyperspectral image (HSI) data are determined and need to be deeply mined. A convolution neural network (CNN) model of two-dimensional spectrum (2D spectrum) is proposed based on the advantages of deep learning to extract feature and classify HSI. First of all, the traditional data processing methods which use small area pixel block or one-dimensional spectral vector as input unit bring many heterogeneous noises. The 2D-spectrum image method is proposed to solve the problem and make full use of spectral value and spatial information. Furthermore, a batch normalization algorithm (BN) is introduced to address internal covariate shifts caused by changes in the distribution of input data and expedite the training of the network. Finally, Softmax loss models are proposed to induce competition among the outputs and improve the performance of the CNN model. The HSI datasets of experiments include Indian Pines, Salinas, Kennedy Space Center (KSC), and Botswana. Experimental results show that the overall accuracies of the 2D-spectrum CNN model can reach 98.26%, 97.28%, 96.22%, and 93.64%. These results are higher than the accuracies of other traditional methods described in this paper. The proposed model can achieve high target classification accuracy and efficiency.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-725X
1687-7268
DOI:10.1155/2018/8602103