Depthwise Separable Residual Network Based on UNet for PolSAR Images Classification
- Resource Type
- Conference
- Authors
- Xie, Wen; Wang, Ruonan; Yang, Xin; Hua, Wenqiang
- Source
- IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium Geoscience and Remote Sensing Symposium, IGARSS 2022 - 2022 IEEE International. :1039-1042 Jul, 2022
- Subject
- Aerospace
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Geoscience
Photonics and Electrooptics
Power, Energy and Industry Applications
Signal Processing and Analysis
Support vector machines
Convolution
Geoscience and remote sensing
Network architecture
Feature extraction
Spatial databases
Polarimetric synthetic aperture radar
Residual structure
depthwise separable convolution
Unet
PolSAR images classification
- Language
- ISSN
- 2153-7003
According to the small sample characteristics of polarimetric synthetic aperture radar (PolSAR) data and its unique data attributes, a new network architecture for PolSAR images classification based on Unet is proposed in this paper. Fully considering the characteristics of PolSAR data, the spatial features and channel features of the input data are extracted respectively by the depthwise separable convolution and avoid extracting redundant features. In order to improve the classification accuracy, the residual structure is used to increase the depth of the network and fully transmit the characteristics information of PolSAR data. The experimental results clearly demonstrate that the architecture we proposed can achieve better classification accuracy than other PolSAR images classification methods.