Next Article in Journal
Nonlocal Tensor Sparse Representation and Low-Rank Regularization for Hyperspectral Image Compressive Sensing Reconstruction
Previous Article in Journal
Hyperspectral Anomaly Detection via Dictionary Construction-Based Low-Rank Representation and Adaptive Weighting
Article Menu
Issue 2 (January-2) cover image

Export Article

Open AccessArticle
Remote Sens. 2019, 11(2), 194; https://doi.org/10.3390/rs11020194

Hyperspectral Image Classification Using Similarity Measurements-Based Deep Recurrent Neural Networks

1
Department of Geography, College of Geosciences, Texas A&M University, College Station, TX 77843, USA
2
Center for Geospatial Sciences, Applications and Technology, Texas A&M University, College Station, TX 77843, USA
3
Department of Computer Science and Engineering, Texas A&M University, College Station, TX 77843, USA
*
Author to whom correspondence should be addressed.
Received: 27 November 2018 / Revised: 28 December 2018 / Accepted: 16 January 2019 / Published: 19 January 2019
(This article belongs to the Section Remote Sensing Image Processing)
Full-Text   |   PDF [4323 KB, uploaded 22 January 2019]   |  

Abstract

Classification is a common objective when analyzing hyperspectral images, where each pixel is assigned to a predefined label. Deep learning-based algorithms have been introduced in the remote-sensing community successfully in the past decade and have achieved significant performance improvements compared with conventional models. However, research on the extraction of sequential features utilizing a single image, instead of multi-temporal images still needs to be further investigated. In this paper, a novel strategy for constructing sequential features from a single image in long short-term memory (LSTM) is proposed. Two pixel-wise-based similarity measurements, including pixel-matching (PM) and block-matching (BM), are employed for the selection of sequence candidates from the whole image. Then, the sequential structure of a given pixel can be constructed as the input of LSTM by utilizing the first several matching pixels with high similarities. The resulting PM-based LSTM and BM-based LSTM are appealing, as all pixels in the whole image are taken into consideration when calculating the similarity. In addition, BM-based LSTM also utilizes local spectral-spatial information that has already shown its effectiveness in hyperspectral image classification. Two common distance measures, Euclidean distance and spectral angle mapping, are also investigated in this paper. Experiments with two benchmark hyperspectral images demonstrate that the proposed methods achieve marked improvements in classification performance relative to the other state-of-the-art methods considered. For instance, the highest overall accuracy achieved on the Pavia University image is 96.20% (using both BM-based LSTM and spectral angle mapping), which is an improvement compared with 84.45% overall accuracy generated by 1D convolutional neural networks. View Full-Text
Keywords: hyperspectral image classification; deep learning; recurrent neural network; spatial similarity measurements; pixel matching; block matching hyperspectral image classification; deep learning; recurrent neural network; spatial similarity measurements; pixel matching; block matching
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

Ma, A.; Filippi, A.M.; Wang, Z.; Yin, Z. Hyperspectral Image Classification Using Similarity Measurements-Based Deep Recurrent Neural Networks. Remote Sens. 2019, 11, 194.

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