Impact of Training Set Design in CNN-Based Sar Image Despeckling

Mazza, A; Scarpa, Giuseppe; Verdoliva, Luisa; Poggi, Gianfranco

doi:10.1109/igarss47720.2021.9553022

Cited by 4 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the purpose of emphasizing sound suggestions for reasonable training, the authors in Ref. 44 evaluated experimentally the influence of training set design on the effectiveness of SAR image despeckling. For SAR image despeckling, 45 presents a dilated residual shrinkage network.…”

Section: Literature Surveymentioning

confidence: 99%

Review on nontraditional perspectives of synthetic aperture radar image despeckling

2022

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) image despeckling is a preprocessing method. SAR images are, by default, noisy in nature. The kind of noise found in SAR images is called speckle noise. The effect of this noise on SAR images is highly adverse. It degrades the quality of the SAR image, resulting in the loss of vital information. Since SAR images are inherently speckled in nature, it costs a lot of information loss. The removal of such noise from the SAR image is mandatory and is the first step. The elimination of speckle noise from SAR images is called SAR image despeckling. There are various traditional and nontraditional methods of SAR image despeckling based on Bayesian and non-Bayesian techniques. The SAR image despeckling methods based on Bayesian techniques are further subdivided into spatial and transform domains. This paper presents a comparative review of nontraditional perspectives on SAR image despeckling. The comparison is made based on methodology, objectives, merits, and demerits. Its focus is to do analysis of all the latest research done in the field of SAR image despeckling using nontraditional methods.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Review on nontraditional perspectives of synthetic aperture radar image despeckling

2022

View full text Add to dashboard Cite

show abstract

“…In doing so, the limitations of the speckle model are notably reduced. The benefits and the drawback related to training deep learning networks on both, synthetic data and on the temporal multi looking approach are addressed in [8].…”

Section: Introductionmentioning

confidence: 99%

“…A comparison with the common approach that relies on using corrupted data by a speckle model invites us to replace such a long-term way of working with the new methodology. This new methodology, although addressed in [8], where is said, sic. "On the contrary, the approach based on simulation is quite risky if the simulated data are not really aligned with the test data", has not been soundly proposed as a new approach to replacing the old ones based on Lee's protocol.…”

Section: Introductionmentioning

confidence: 99%

A New Methodology for Assessing SAR Despeckling Filters

Vásquez-Salazar,

Cardona-Mesa,

Gómez

et al. 2024

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Supervised learning requires labeled data to train models and then make predictions from new input data. Deep Learning (DL) methods require immense amounts of training data and processing power to provide reasonable results. In computer vision applications, and more specifically in despeckling SAR (Synthetic Aperture Radar) images, due to the speckle content, there is no ground truth available. To test the performances of despeckling filters, the common approach is to corrupt synthetic images with a suitable speckle model and then, after filtering, well-known metrics are obtained. Then, filters are tested on actual SAR data, and specific metrics for SAR are evaluated. However, even the most elaborated speckle models are far from accounting for the complex mechanisms related to SAR images. In this paper, a methodology to design a realistic dataset to overcome these limitations is proposed. Actual SAR images of the same scene but acquired with the same sensor on different dates are downloaded from one of the available satellite platforms. Images are properly co-registered and averaged to get a ground truth-like reference image to objectively evaluate the performance of a despeckling method. To show the benefits of the proposed methodology, an on-the-shelf deep learning approach is used to filter the data, and compared with the standard approach using synthetic corrupted images with a speckle model. The final validation on actual SAR data not included in the training phase validates the proposed dataset. From the results shown, it is recommended to test filters on the proposed more realistic dataset and abandon the usual approach.

show abstract

“…Except for the matrix/tensor completion methods, machine learning and deep learning [35,36] are also typical ways to remove clouds. For example, Singh and Komodakis propose a cloud removal generative adversarial network (GAN) to learn the mapping between cloudy images and cloud-free images [37].…”

Section: Introductionmentioning

confidence: 99%

Fast Thick Cloud Removal for Multi-Temporal Remote Sensing Imagery via Representation Coefficient Total Variation

Xu,

Wang,

Wang

2023

Remote Sensing

View full text Add to dashboard Cite

Although thick cloud removal is a complex task, the past decades have witnessed the remarkable development of tensor-completion-based techniques. Nonetheless, they require substantial computational resources and may suffer from checkboard artifacts. This study presents a novel technique to address this challenging task using representation coefficient total variation (RCTV), which imposes a total variation regularizer on decomposed data. The proposed approach enhances cloud removal performance while effectively preserving the textures with high speed. The experimental results confirm the efficiency of our method in restoring image textures, demonstrating its superior performance compared to state-of-the-art techniques.

show abstract

Impact of Training Set Design in CNN-Based Sar Image Despeckling

Cited by 4 publications

References 15 publications

Review on nontraditional perspectives of synthetic aperture radar image despeckling

Review on nontraditional perspectives of synthetic aperture radar image despeckling

A New Methodology for Assessing SAR Despeckling Filters

Fast Thick Cloud Removal for Multi-Temporal Remote Sensing Imagery via Representation Coefficient Total Variation

Contact Info

Product

Resources

About