Multiscale Spatial-Spectral Convolutional Network with Image-Based Framework for Hyperspectral Imagery Classification

Multiscale Spatial-Spectral Convolutional Network with Image-Based Framework for Hyperspectral Imagery Classification

Jointly using spatial and spectral information has been widely applied to hyperspectral image (HSI) classification. Especially, convolutional neural networks (CNN) have gained attention in recent years due to their detailed representation of features. However, most of CNN-based HSI classification me...

Full description

Bibliographic Details
Main Authors: Ximin Cui, Ke Zheng, Lianru Gao, Bing Zhang, Dong Yang, Jinchang Ren
Format: Article
Language:English
Published: MDPI AG 2019-09-01
Series:Remote Sensing
Subjects:
hyperspectral image classification
convolutional neural network
multiscale spatial-spectral features
spatial neighbor feature extraction
dilation convolution
feature pyramid
Online Access:https://www.mdpi.com/2072-4292/11/19/2220

Internet

https://www.mdpi.com/2072-4292/11/19/2220

Similar Items