SAR Image Despeckling Based on Block-Matching and Noise-Referenced Deep Learning Method

Abstract

The noise2noise-based despeckling method, capable of training the despeckling deep neural network with only noisy synthetic aperture radar (SAR) image, has presented very good performance in recent research. This method requires a fine-registered multi-temporal dataset with minor time variance and uses similarity estimation to compensate for the time variance. However, constructing such a training dataset is very time-consuming and may not be viable for a certain practitioner. In this article, we propose a novel single-image-capable speckling method that combines the similarity-based block-matching and noise referenced deep learning network. The denoising network designed for this method is an encoder–decoder convolutional neural network and is accommodated to small image patches. This method firstly constructs a large number of noisy pairs as training input by similarity-based block-matching in either one noisy SAR image or multiple images. Then, the method trains the network in a Siamese manner with two parameter-sharing branches. The proposed method demonstrates favorable despeckling performance with both simulated and real SAR data with respect to other state-of-the-art reference filters. It also presents satisfying generalization capability as the trained network can despeckle well the unseen image of the same sensor. The main advantage of the proposed method is its application flexibility. It could be trained with either one noisy image or multiple images. Furthermore, the despeckling could be inferred by either the ad hoc trained network or a pre-trained one of the same sensor.

Review on nontraditional perspectives of synthetic aperture radar image despeckling

“…4,31 After that, methods like 1,3 also show great results. The results of 29,34,38 are also satisfactory. While rest of the methods shows below satisfactory results.…”

“…This detailed comparison is performed on some prevalent methods. 1,3,4,29,31,34,38,39,46,54,[62][63][64][65][66][67]…”

“…Figures 5 and 6 show the despeckling result of some of efficient latest nontraditional methods. 1,3,4,29,31,34,38,39,46,54 This comparison is made based on the visual quality of despeckling results and different metrics used for the performance analysis of these methods. The speckled SAR images taken for reference for the despeckling demonstration are shown in Figs.…”

“…5(h) and 5(j). Also, noise variance looks higher even after despeckling process, as distortion is clearly 29 (e) 2022, 31 (f) 2022, 34 (g) 2021, 38 (h) 2021, 39 (i) 2021, 46 and (j) 2019. 54 Fig.…”

“…54 Fig. 6 Despeckling results (a) 2018, 1 (b) 2020, 3 (c) 2021, 4 (d) 2022, 29 (e) 2022, 31 (f) 2022, 34 (g) 2021, 38 (h) 2021, 39 (i) 2021, 46 and (j) 2019. 54 Singh, Shankar, and Diwakar: Review on nontraditional perspectives of synthetic aperture radar image.…”