Complexity Analysis of an Edge Preserving CNN SAR Despeckling Algorithm

SAR images are affected by multiplicative noise that impairs their interpretations. In the last decades several methods for SAR denoising have been proposed and in the last years great attention has moved towards deep learning based solutions. Based on our last proposed convolutional neural network for SAR despeckling, here we exploit the effect of the complexity of the network. More precisely, once a dataset has been fixed, we carry out an analysis of the network performance with respect to the number of layers and numbers of features the network is composed of. Evaluation on simulated and real data are carried out. The results show that deeper networks better generalize on both simulated and real images.

[1]  Vishal M. Patel,et al.  SAR Image Despeckling Using a Convolutional Neural Network , 2017, IEEE Signal Processing Letters.

[2]  Shawn D. Newsam,et al.  Bag-of-visual-words and spatial extensions for land-use classification , 2010, GIS '10.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[5]  Giampaolo Ferraioli,et al.  Ratio-Based Nonlocal Anisotropic Despeckling Approach for SAR Images , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Alejandro C. Frery,et al.  Unassisted Quantitative Evaluation of Despeckling Filters , 2017, Remote. Sens..

[7]  Giampaolo Ferraioli,et al.  Edge Preserving Cnn Sar Despeckling Algorithm , 2020, 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS).

[8]  Giampaolo Ferraioli,et al.  Ultrasound despeckling based on Non Local Means , 2017 .

[9]  Giampaolo Ferraioli,et al.  The Role of Nonlocal Estimation in SAR Tomographic Imaging of Volumetric Media , 2018, IEEE Geoscience and Remote Sensing Letters.

[10]  H. Aghababaee,et al.  The use of NL paradigm in SAR applications , 2019, 2019 IEEE 5th International forum on Research and Technology for Society and Industry (RTSI).

[11]  Giampaolo Ferraioli,et al.  Multi-Objective CNN-Based Algorithm for SAR Despeckling , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Giuseppe Scarpa,et al.  TanDEM-X Forest Mapping Using Convolutional Neural Networks , 2019, Remote. Sens..

[13]  Luciano Alparone,et al.  A Tutorial on Speckle Reduction in Synthetic Aperture Radar Images , 2013, IEEE Geoscience and Remote Sensing Magazine.

[14]  Davide Cozzolino,et al.  SAR image despeckling through convolutional neural networks , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[15]  Giampaolo Ferraioli,et al.  A Novel Cost Function for Despeckling using Convolutional Neural Networks , 2019, 2019 Joint Urban Remote Sensing Event (JURSE).

[16]  Luisa Verdoliva,et al.  Exploiting Patch Similarity for SAR Image Processing: The nonlocal paradigm , 2014, IEEE Signal Processing Magazine.

[17]  Giampaolo Ferraioli,et al.  A New Ratio Image Based CNN Algorithm for SAR Despeckling , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[18]  G. Schirinzi,et al.  Sar Tomography Based on Deep Learning , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[19]  Davide Cozzolino,et al.  Guided Patchwise Nonlocal SAR Despeckling , 2018, IEEE Transactions on Geoscience and Remote Sensing.