Segmentation-Guided Semantic-Aware Self-Supervised Denoising for SAR Image
- 13 October 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-16
Abstract
Synthetic aperture radar (SAR) images often suffer from speckle noise, which can degrade their visual quality and affect downstream applications. Recently, supervised and self-supervised methods have been proposed by virtue of deep learning with synthetic “noisy-clean” image pairs or only real noisy images as training data, respectively. Among these methods, by avoiding artifact problems in real SAR image denoising, self-supervised methods solve the domain gap problem of supervised methods and hence have attracted significant attention. However, existing self-supervised denoising methods essentially rely on pixel information of images and ignore corresponding semantic information, which makes them challenging to remove speckle noise while retaining detailed features. To this end, we propose a segmentation-guided semantic-aware self-supervised denoising method for SAR images, namely SARDeSeg, where a segmentation network is incorporated with a denoising network and guides it to learn and be aware of the semantic information of the input noisy SAR images. Additionally, a wavelet transform-based connector is introduced to efficiently transmit semantic information between the denoising network and the segmentation network, together with an edge-aware smoothing loss to improve speckle noise suppression while preserving edge features. Experimental results demonstrate that the proposed SARDeSeg outperforms state-of-the-art denoising methods for SAR images, particularly in preserving detailed edge features.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (3072021CFT0602)
- Natural Science Foundation of Heilongjiang Province (JJ2019LH2160)
- Fundamental Research Funds for the Central Universities–Research and Innovation Fund for Doctoral Students
This publication has 39 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the ArtIEEE Geoscience and Remote Sensing Magazine, 2016
- SAR Image Despeckling by the Use of Variational Methods With Adaptive Nonlocal FunctionalsIEEE Transactions on Geoscience and Remote Sensing, 2016
- Change Detection in Synthetic Aperture Radar Images Based on Deep Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2015
- Deep learningNature, 2015
- A Nonlocal Structure Tensor-Based Approach for Multicomponent Image Recovery ProblemsIEEE Transactions on Image Processing, 2014
- Bag-of-visual-words and spatial extensions for land-use classification2010
- Multiplicative Noise Removal Using Variable Splitting and Constrained OptimizationIEEE Transactions on Image Processing, 2010
- Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based WeightsIEEE Transactions on Image Processing, 2009
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002