A CNN-Based Self-Supervised Synthetic Aperture Radar Image Denoising Approach
- 24 August 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-15
Abstract
Synthetic aperture radar (SAR) plays an essential role in earth observation and projection due to its capability to penetrate clouds, which makes it possible to monitor terrestrial surfaces under all weather conditions. Multiplicative noise often occurs in the SAR signal, hampering the retrieval of information from SAR imagery. Convolutional neural networks (CNNs) have been used in many computer vision tasks and are helpful in image denoising. However, current CNN-based denoising approaches inevitably lead to a “washed out” effect that loses spatial details. Another limitation is that most typical CNN-based denoising models require a noise-free image for training. To address these issues, we propose a novel end-to-end self-supervised SAR denoising model: Enhanced Noise2Noise (EN2N), which can be trained without a noise-free image. To enhance the quality of the result images, the perceptual features from a pre-learned CNN are introduced to restore the spatial details by a hybrid loss function. Experiments show that our proposed method outperforms the typical denoising methods in terms of noise reduction and feature preservation based on image quality metrics. Also, the new hybrid loss could enhance the spatial details significantly. The good performance maintains the robustness throughout time, which reduces the uncertainty in time-series SAR caused by random noise. Benefiting from optimization of graphics processing unit (GPU) and multi-threading, the proposed method has higher computation efficiency than traditional methods. This study demonstrates the great potential of using our self-supervised deep learning approaches for SAR image denoising in the future.Keywords
Funding Information
- National Key Research and Development Program of China (2018YFE0107000)
- National Key Research and Development Program of China (2016YFA0600301)
- National Natural Science Foundation of China (42001356)
This publication has 59 references indexed in Scilit:
- Mapping paddy rice agriculture in southern China using multi-temporal MODIS imagesRemote Sensing of Environment, 2005
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- The shuttle radar topography mission—a new class of digital elevation models acquired by spaceborne radarISPRS Journal of Photogrammetry and Remote Sensing, 2003
- A review of speckle filtering in the context of estimation theoryIEEE Transactions on Geoscience and Remote Sensing, 2002
- Filtering of multichannel SAR imagesIEEE Transactions on Geoscience and Remote Sensing, 2001
- Rice monitoring and production estimation using multitemporal RADARSATRemote Sensing of Environment, 2001
- Multitemporal ERS SAR analysis applied to forest mappingIEEE Transactions on Geoscience and Remote Sensing, 2000
- Speckle filtering of synthetic aperture radar images: A reviewRemote Sensing Reviews, 1994
- Speckle reduction in multipolarization, multifrequency SAR imageryIEEE Transactions on Geoscience and Remote Sensing, 1991
- Adaptive speckle filters and scene heterogeneityIEEE Transactions on Geoscience and Remote Sensing, 1990