Abstract
Speckle removal process is inevitable in the restoration of synthetic aperture radar (SAR) images. Several variant methods have been proposed for enhancing SAR images over the past decades. However, in recent studies, convolutional neural networks (CNNs) have been widely applied in SAR image despeckling because of their versatility in representation learning. Nonetheless, a fair number of textures of the images are still lost when despeckling using simple CNN structures. To solve this problem, an encoder–decoder architecture was previously proposed. Although this architecture extracts features on different scales and has been shown to yield state-of-the-art performance, it still learns representation locally, resulting in missing overall information of convolutional features. Therefore, we herein introduce a new method for SAR image despeckling (SAR-CAM), which improves the performance of an encoder–decoder CNN architecture by using various attention modules. Moreover, a context block is introduced at the minimum scale to capture multiscale information. The model is trained via a data-driven approach using the gradient descent algorithm with a combination of modified despeckling gain and total variation loss function. Experiments performed on simulated and real SAR data demonstrate that the proposed method achieves significant improvements over state-of-the-art methodologies.
Highlights
S YNTHETIC apeture radars (SARs), which are active coherent systems, can cover a broad spectrum of extensive areas having varied geographical features
To further improve the accuracy of the speckle noise suppression model, we introduce a modified despeckling gain (DG) loss in which an extra logarithmic scale was added to the original function to prevent gradient exploding obstacles
convolutional neural networks (CNNs) models, which surpass the performance of nonlocal means (NLM) methods, have become a major approach for restoring speckled images
Summary
S YNTHETIC apeture radars (SARs), which are active coherent systems, can cover a broad spectrum of extensive areas having varied geographical features. Scholars began to work on speckle noise reduction schemes since the early 1980s, starting from spatial domain filters, which include Lee filter [3], Kuan filter [4], Frost filter [5], and Gamma MAP filter [6], where [3]–[5] are derived from a minimum mean square error (MMSE) whilst [6] employed a maximum a posteriori (MAP) filter Because these filters function by expecting a linear connection between the result and the original image, edge and texture details in SAR images are commonly lost
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.