Next Article in Journal
Evaluation of the Stability of the Darbandikhan Dam after the 12 November 2017 Mw 7.3 Sarpol-e Zahab (Iran–Iraq Border) Earthquake
Next Article in Special Issue
Multi-Stream Convolutional Neural Network for SAR Automatic Target Recognition
Previous Article in Journal
WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging and Deep Neural Network for Precision Farming
Previous Article in Special Issue
A Super-Resolution and Fusion Approach to Enhancing Hyperspectral Images
Article Menu

Export Article

Open AccessArticle
Remote Sens. 2018, 10(9), 1425; https://doi.org/10.3390/rs10091425

Hyperspectral Image Classification Based on Parameter-Optimized 3D-CNNs Combined with Transfer Learning and Virtual Samples

1
College of Automation & Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, China
2
Institute Fresnel, Ecole Centrale de Marseille, 13013 Marseille, France
3
College of Information Science & Engineering, Ocean University of China, Qingdao 266100, China
*
Author to whom correspondence should be addressed.
Received: 26 July 2018 / Revised: 31 August 2018 / Accepted: 5 September 2018 / Published: 7 September 2018
Full-Text   |   PDF [5130 KB, uploaded 17 September 2018]   |  

Abstract

Recent research has shown that spatial-spectral information can help to improve the classification of hyperspectral images (HSIs). Therefore, three-dimensional convolutional neural networks (3D-CNNs) have been applied to HSI classification. However, a lack of HSI training samples restricts the performance of 3D-CNNs. To solve this problem and improve the classification, an improved method based on 3D-CNNs combined with parameter optimization, transfer learning, and virtual samples is proposed in this paper. Firstly, to optimize the network performance, the parameters of the 3D-CNN of the HSI to be classified (target data) are adjusted according to the single variable principle. Secondly, in order to relieve the problem caused by insufficient samples, the weights in the bottom layers of the parameter-optimized 3D-CNN of the target data can be transferred from another well trained 3D-CNN by a HSI (source data) with enough samples and the same feature space as the target data. Then, some virtual samples can be generated from the original samples of the target data to further alleviate the lack of HSI training samples. Finally, the parameter-optimized 3D-CNN with transfer learning can be trained by the training samples consisting of the virtual and the original samples. Experimental results on real-world hyperspectral satellite images have shown that the proposed method has great potential prospects in HSI classification. View Full-Text
Keywords: remote sensing image; convolutional neural network; optimal parameter; lack of sample; tensor analysis remote sensing image; convolutional neural network; optimal parameter; lack of sample; tensor analysis
Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Liu, X.; Sun, Q.; Meng, Y.; Fu, M.; Bourennane, S. Hyperspectral Image Classification Based on Parameter-Optimized 3D-CNNs Combined with Transfer Learning and Virtual Samples. Remote Sens. 2018, 10, 1425.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top