The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-3/W12-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W12-2020, 97–100, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-97-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W12-2020, 97–100, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-97-2020

  04 Nov 2020

04 Nov 2020

EDGE PRESERVING CNN SAR DESPECKLING ALGORITHM

S. Vitale1, G. Ferraioli2, and V. Pascazio1 S. Vitale et al.
  • 1Università degli Studi di Napoli Parthenope, Dipartimento di Ingegneria, Napoli, Italy
  • 2Università degli Studi di Napoli Parthenope, Dipartimento di Scienze e Tecnologie, Napoli, Italy

Keywords: SAR, deep learning, speckle, cnn, denoising

Abstract. SAR despeckling is a key tool for Earth Observation. Interpretation of SAR images are impaired by speckle, a multiplicative noise related to interference of backscattering from the illuminated scene towards the sensor. Reducing the noise is a crucial task for the understanding of the scene. Based on the results of our previous solution KL-DNN, in this work we define a new cost function for training a convolutional neural network for despeckling. The aim is to control the edge preservation and to better filter man-made structures and urban areas that are very challenging for KL-DNN. The results show a very good improvement on the not homogeneous areas keeping the good results in the homogeneous ones. Result on both simulated and real data are shown in the paper.