SAR image despeckling through convolutional neural networks

• Published in: IEEE International Geoscience and Remote Sensing Symposium proceedings pp. 5438 - 5441
• Main Authors: Chierchia, G., Cozzolino, D., Poggi, G., Verdoliva, L.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2017
• Subjects: convolutional neural networks; Indexes; multiplicative noise; Noise measurement; Remote sensing; SAR; Speckle; Synthetic aperture radar; Training
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS.2017.8128234

In this paper we investigate the use of discriminative model learning through Convolutional Neural Networks (CNNs) for SAR image despeckling. The network uses a residual learning strategy, hence it does not recover the filtered image, but the speckle component, which is then subtracted from the noisy one. Training is carried out by considering a large multitemporal SAR image and its multilook version, in order to approximate a clean image. Experimental results, both on synthetic and real SAR data, show the method to achieve better performance with respect to state-of-the-art techniques.