PolSAR Image Classification with Lightweight 3D Convolutional Networks
Convolutional neural networks (CNNs) have become the state-of-the-art in optical image processing. Recently, CNNs have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. Unlike optical images, the unique phase information of PolSAR data e...
Main Authors: | Hongwei Dong, Lamei Zhang, Bin Zou |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/3/396 |
Similar Items
-
Deep Fuzzy Graph Convolutional Networks for PolSAR Imagery Pixelwise Classification
by: Hongying Liu, et al.
Published: (2021-01-01) -
A Novel Deep Fully Convolutional Network for PolSAR Image Classification
by: Yangyang Li, et al.
Published: (2018-12-01) -
Graph Convolutional Networks by Architecture Search for PolSAR Image Classification
by: Hongying Liu, et al.
Published: (2021-04-01) -
Semi-Supervised Classification for PolSAR Data With Multi-Scale Evolving Weighted Graph Convolutional Network
by: Shijie Ren, et al.
Published: (2021-01-01) -
PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features
by: Xinzheng Zhang, et al.
Published: (2019-08-01)