Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

A High-Performance Spectral-Spatial Residual Network for Hyperspectral Image Classification with Small Training Data

Khotimah, W.N., Bennamoun, M., Boussaid, F., Sohel, F. and Edwards, D. (2020) A High-Performance Spectral-Spatial Residual Network for Hyperspectral Image Classification with Small Training Data. Remote Sensing, 12 (19). Art. 3137.

[img]
Preview
PDF - Published Version
Download (1MB) | Preview
Free to read: https://doi.org/10.3390/RS12193137
*No subscription required

Abstract

In this paper, we propose a high performance Two-Stream spectral-spatial Residual Network (TSRN) for hyperspectral image classification. The first spectral residual network (sRN) stream is used to extract spectral characteristics, and the second spatial residual network (saRN) stream is concurrently used to extract spatial features. The sRN uses 1D convolutional layers to fit the spectral data structure, while the saRN uses 2D convolutional layers to match the hyperspectral spatial data structure. Furthermore, each convolutional layer is preceded by a Batch Normalization (BN) layer that works as a regularizer to speed up the training process and to improve the accuracy. We conducted experiments on three well-known hyperspectral datasets, and we compare our results with five contemporary methods across various sizes of training samples. The experimental results show that the proposed architecture can be trained with small size datasets and outperforms the state-of-the-art methods in terms of the Overall Accuracy, Average Accuracy, Kappa Value, and training time.

Item Type: Journal Article
Murdoch Affiliation: Information Technology, Mathematics and Statistics
Publisher: MDPI
Copyright: © 2020 MDPI
URI: http://researchrepository.murdoch.edu.au/id/eprint/58333
Item Control Page Item Control Page

Downloads

Downloads per month over past year