Next Article in Journal
A Simple Method for Converting 1-km Resolution Daily Clear-Sky LST into Real LST
Previous Article in Journal
An Iterative ICA-Based Reconstruction Method to Produce Consistent Time-Variable Total Water Storage Fields Using GRACE and Swarm Satellite Data
Open AccessArticle

Spatial-Adaptive Siamese Residual Network for Multi-/Hyperspectral Classification

by Zhi He 1,* and Dan He 2
Guangdong Provincial Key Laboratory of Urbanization and Geo-Simulation, Center of Integrated Geographic Information Analysis, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), School of Geography and Planning, Sun Yat-sen University, Guangzhou 510275, China
City College of Dongguan University of Technology, Dongguan 511700, China
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(10), 1640;
Received: 12 April 2020 / Revised: 12 May 2020 / Accepted: 16 May 2020 / Published: 20 May 2020
Deep learning methods have been successfully applied for multispectral and hyperspectral images classification due to their ability to extract hierarchical abstract features. However, the performance of these methods relies heavily on large-scale training samples. In this paper, we propose a three-dimensional spatial-adaptive Siamese residual network (3D-SaSiResNet) that requires fewer samples and still enhances the performance. The proposed method consists of two main steps: construction of 3D spatial-adaptive patches and Siamese residual network for multiband images classification. In the first step, the spectral dimension of the original multiband images is reduced by a stacked autoencoder and superpixels of each band are obtained by the simple linear iterative clustering (SLIC) method. Superpixels of the original multiband image can be finally generated by majority voting. Subsequently, the 3D spatial-adaptive patch of each pixel is extracted from the original multiband image by reference to the previously generated superpixels. In the second step, a Siamese network composed of two 3D residual networks is designed to extract discriminative features for classification and we train the 3D-SaSiResNet by pairwise inputting the training samples into the networks. The testing samples are then fed into the trained 3D-SaSiResNet and the learned features of the testing samples are classified by the nearest neighbor classifier. Experimental results on three multiband image datasets show the feasibility of the proposed method in enhancing classification performance even with limited training samples. View Full-Text
Keywords: remote sensing; classification; stacked autoencoder; superpixel; Siamese network remote sensing; classification; stacked autoencoder; superpixel; Siamese network
Show Figures

Graphical abstract

MDPI and ACS Style

He, Z.; He, D. Spatial-Adaptive Siamese Residual Network for Multi-/Hyperspectral Classification. Remote Sens. 2020, 12, 1640.

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.

Article Access Map by Country/Region

Search more from Scilit
Back to TopTop