Dual-Channel Convolution Network With Image-Based Global Learning Framework for Hyperspectral Image Classification
- 30 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
Recently, convolutional neural networks (CNNs) have been widely applied to hyperspectral image (HSI) classification due to their detailed representation of features. Nevertheless, the current CNN-based HSI classification methods mainly follow a patch-based learning framework. These methods are nonglobal learning methods, which not only limit the use of global information but also require a high computational cost. In this letter, an image-based global learning framework is introduced to HSI classification. Based on this framework, we propose a dual-channel convolutional network (DCCN) for HSI classification to maximize the exploitation of the global and multiscale information of HSI. The experimental results conducted on two real hyperspectral datasets indicate that our method is superior to other related methods in terms of both efficiency and accuracy for HSI classification.Keywords
Funding Information
- National Natural Science Foundation of China (42101350, 41901304)
- China Postdoctoral Science Foundation (2020M680925, 2021M693234)
This publication has 14 references indexed in Scilit:
- Vicarious Calibration for the AHSI Instrument of Gaofen-5 With Reference to the CRCS Dunhuang Test SiteIEEE Transactions on Geoscience and Remote Sensing, 2020
- Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism NetworkRemote Sensing, 2020
- 3-D Deep Learning Approach for Remote Sensing Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2018
- Hyperspectral Image Classification With Deep Feature Fusion NetworkIEEE Transactions on Geoscience and Remote Sensing, 2018
- Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning FrameworkIEEE Transactions on Geoscience and Remote Sensing, 2017
- Multiscale Superpixel-Level Subspace-Based Support Vector Machines for Hyperspectral Image ClassificationIEEE Geoscience and Remote Sensing Letters, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Class-Dependent Sparse Representation Classifier for Robust Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2014
- Spectral–Spatial Hyperspectral Image Segmentation Using Subspace Multinomial Logistic Regression and Markov Random FieldsIEEE Transactions on Geoscience and Remote Sensing, 2011
- Adaptive Markov Random Field Approach for Classification of Hyperspectral ImageryIEEE Geoscience and Remote Sensing Letters, 2011