Deep Convolutional Capsule Network for Hyperspectral Image Spectral and Spectral-Spatial Classification
Open Access
- 22 January 2019
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 11 (3) , 223
Abstract
Capsule networks can be considered to be the next era of deep learning and have recently shown their advantages in supervised classification. Instead of using scalar values to represent features, the capsule networks use vectors to represent features, which enriches the feature presentation capability. This paper introduces a deep capsule network for hyperspectral image (HSI) classification to improve the performance of the conventional convolutional neural networks (CNNs). Furthermore, a modification of the capsule network named Conv-Capsule is proposed. Instead of using full connections, local connections and shared transform matrices, which are the core ideas of CNNs, are used in the Conv-Capsule network architecture. In Conv-Capsule, the number of trainable parameters is reduced compared to the original capsule, which potentially mitigates the overfitting issue when the number of available training samples is limited. Specifically, we propose two schemes: (1) A 1D deep capsule network is designed for spectral classification, as a combination of principal component analysis, CNN, and the Conv-Capsule network, and (2) a 3D deep capsule network is designed for spectral-spatial classification, as a combination of extended multi-attribute profiles, CNN, and the Conv-Capsule network. The proposed classifiers are tested on three widely-used hyperspectral data sets. The obtained results reveal that the proposed models provide competitive results compared to the state-of-the-art methods, including kernel support vector machines, CNNs, and recurrent neural network.Keywords
Funding Information
- National Natural Science Foundation of China (61771171)
This publication has 41 references indexed in Scilit:
- Advanced Spectral Classifiers for Hyperspectral Images: A reviewIEEE Geoscience and Remote Sensing Magazine, 2017
- Nonlinear Multiple Kernel Learning With Multiple-Structure-Element Extended Morphological Profiles for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2016
- Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing ImageryRemote Sensing, 2015
- A Discontinuity Preserving Relaxation Scheme for Spectral–Spatial Hyperspectral Image ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- A Survey on Spectral–Spatial Classification Techniques Based on Attribute ProfilesIEEE Transactions on Geoscience and Remote Sensing, 2014
- Slow Feature Analysis for Change Detection in Multispectral ImageryIEEE Transactions on Geoscience and Remote Sensing, 2013
- Airborne hyperspectral remote sensing to assess spatial distribution of water quality characteristics in large rivers: The Mississippi River and its tributaries in MinnesotaRemote Sensing of Environment, 2013
- Updating Land-Cover Maps by Classification of Image Time Series: A Novel Change-Detection-Driven Transfer Learning ApproachIEEE Transactions on Geoscience and Remote Sensing, 2012
- Application of Model-Based Change Detection to Airborne VNIR/SWIR Hyperspectral ImageryIEEE Transactions on Geoscience and Remote Sensing, 2012
- Opportunities and limitations for image-based remote sensing in precision crop managementRemote Sensing of Environment, 1997