Back to Search Start Over

Despeckling Polarimetric SAR Data Using a Multistream Complex-Valued Fully Convolutional Network

Authors :
Johannes Reiche
Adugna G. Mullissa
Claudio Persello
Department of Earth Observation Science
UT-I-ITC-ACQUAL
Faculty of Geo-Information Science and Earth Observation
Source :
IEEE Geoscience and Remote Sensing Letters 19 (2022), IEEE Geoscience and Remote Sensing Letters, 19, 1-5, IEEE geoscience and remote sensing letters, 19, 1-5. IEEE
Publication Year :
2022

Abstract

A polarimetric synthetic aperture radar (PolSAR) sensor is able to collect images in different polarization states, making it a rich source of information for target characterization. PolSAR images are inherently affected by speckle. Therefore, before deriving ad hoc products from the data, the polarimetric covariance matrix needs to be estimated by reducing speckle. In recent years, deep learning-based despeckling methods have started to evolve from single-channel SAR images to PolSAR images. To this aim, deep learning-based approaches separate the real and imaginary components of the complex-valued covariance matrix and use them as independent channels in standard convolutional neural networks (CNNs). However, this approach neglects the mathematical relationship that exists between the real and imaginary components, resulting in suboptimal output. Here, we propose a multistream complex-valued fully convolutional network (FCN) (CV-deSpeckNet1) to reduce speckle and effectively estimate the PolSAR covariance matrix. To evaluate the performance of CV-deSpeckNet, we used Sentinel-1 dual polarimetric SAR images to compare against its real-valued counterpart that separates the real and imaginary parts of the complex covariance matrix. CV-deSpeckNet was also compared against the state of the art PolSAR despeckling methods. The results show that CV-deSpeckNet was able to be trained with a fewer number of samples, has a higher generalization capability, and resulted in higher accuracy than its real-valued counterpart and state-of-the-art PolSAR despeckling methods. These results showcase the potential of complex-valued deep learning for PolSAR despeckling.

Details

Language :
English
ISSN :
1545598X
Volume :
19
Database :
OpenAIRE
Journal :
IEEE Geoscience and Remote Sensing Letters
Accession number :
edsair.doi.dedup.....3785be0c706f327e7e6280dfc31b5177
Full Text :
https://doi.org/10.1109/lgrs.2021.3066311