Spectral-Spatial Classification of Hyperspectral Imagery Based on Stacked Sparse Autoencoder and Random Forest

Spectral-Spatial Classification of Hyperspectral Imagery Based on Stacked Sparse Autoencoder and Random Forest

It is of great interest in exploiting spectral-spatial information for hyperspectral image (HSI) classification at different spatial resolutions. This paper proposes a new spectral-spatial deep learning-based classification paradigm. First, pixel-based scale transformation and class separability cri...

Full description

Bibliographic Details
Main Authors: Chunhui Zhao, Xiaoqing Wan, Genping Zhao, Bing Cui, Wu Liu, Bin Qi
Format: Article
Language:English
Published: Taylor & Francis Group 2017-01-01
Series:European Journal of Remote Sensing
Subjects:
Classification
hyperspectral imagery
class separability
stacked sparse autoencoder (SSA)
random forest (RF)
Online Access:http://dx.doi.org/10.1080/22797254.2017.1274566

Internet

http://dx.doi.org/10.1080/22797254.2017.1274566

Similar Items