Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives

Abstract

This is the pre-acceptance version, to read the final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE XPlore.Deep learning in remote sensing has become an international hype, but it is mostly limited to the evaluation of optical data. Although deep learning has been introduced in Synthetic Aperture Radar (SAR) data processing, despite successful first attempts, its huge potential remains locked. In this paper, we provide an introduction to the most relevant deep learning models and concepts, point out possible pitfalls by analyzing special characteristics of SAR data, review the state-of-the-art of deep learning applied to SAR in depth, summarize available benchmarks, and recommend some important future research directions. With this effort, we hope to stimulate more research in this interesting yet under-exploited research field and to pave the way for use of deep learning in big SAR data processing workflows.

Hyperanalytic Wavelet-Based Robust Edge Detection

“…Deep learning in remote sensing has become a modern direction of research, but it is mostly limited to the evaluation of optical data [65]. The development of more powerful computing devices and the increase of data availability has led to substantial advances in machine learning (ML) methods.…”

“…In the following, we present some of the ML methods for despeckling, found in two very recent references, firstly in [65]. Inspired by the success of image denoising using a residual learning network architecture in the computer vision community, [66] in [67] was introduced a residual learning Convolutional Neural Network (CNN) for SAR image despeckling, named SAR-CNN, a 17-layered CNN for learning to subtract speckle components from noisy images in a homomorphic framework.…”

“…Based on [65] and [77], it can be observed that most ML-based despeckling methods employ CNN-based architectures with single images of the scene for training; they either output the clean image in an end-to-end fashion or propose residual-based techniques to learn the underlying noise model.…”

A Novel Quality-Guided Two-Dimensional InSAR Phase Unwrapping Method via GAUNet

“…Constant mean coherence ranging from 0.4 to 1 with 0.05 as the interval is used to add noise into the simulated interferometric phase. For data sets 2, the parameters obtained from real interferograms are used to simulate the interferometric phase referring to equation (10). Because of the large quantity, the specific details of the simulated parameters will not be explained here for simplicity.…”

“…However, the applications of deep learning in remote sensing mainly concentrate in optical remote sensing, whereas there are few applications in radar remote sensing especially InSAR [8], [9]. Recently, some researchers in InSAR field are actively exploring the combination of deep learning and InSAR, attempting to draw support from deep learning to solve the problems existing in traditional InSAR technique [10]. Hitherto, DL-based phase unwrapping methods have shown their elegant demeanor.…”