Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image Classification

The deep convolution neural network (CNN), which has prominent advantages in feature learning, can learn and extract features from data automatically. Existing polarimetric synthetic aperture radar (PolSAR) image classification methods based on the CNN only consider the polarization information of t...

Full description

Bibliographic Details
Main Authors: Fei Gao, Teng Huang, Jun Wang, Jinping Sun, Amir Hussain, Erfu Yang
Format: Article
Language:English
Published: MDPI AG 2017-04-01
Series:Applied Sciences
Subjects:
Online Access:http://www.mdpi.com/2076-3417/7/5/447