Near-filed SAR Image Restoration with Deep Learning Inverse Technique: A Preliminary Study

TL;DR

This paper explores a deep learning inverse technique for near-field SAR image restoration, addressing limitations of traditional methods by modeling spatially variable degradation and demonstrating improved shape and energy recovery in simulated experiments.

Contribution

It introduces a novel deep learning approach that models the near-field SAR degradation process as a spatially variable convolution, enhancing image restoration performance.

Findings

Deep learning model outperforms traditional methods in shape recovery.

The approach effectively models spatially variable system responses.

Simulated experiments validate the method's superiority.

Abstract

Benefiting from a relatively larger aperture's angle, and in combination with a wide transmitting bandwidth, near-field synthetic aperture radar (SAR) provides a high-resolution image of a target's scattering distribution-hot spots. Meanwhile, imaging result suffers inevitable degradation from sidelobes, clutters, and noises, hindering the information retrieval of the target. To restore the image, current methods make simplified assumptions; for example, the point spread function (PSF) is spatially consistent, the target consists of sparse point scatters, etc. Thus, they achieve limited restoration performance in terms of the target's shape, especially for complex targets. To address these issues, a preliminary study is conducted on restoration with the recent promising deep learning inverse technique in this work. We reformulate the degradation model into a spatially variable complex-convolution model, where the near-field SAR's system response is considered. Adhering to it, a model-based deep learning network is designed to restore the image. A simulated degraded image dataset from multiple complex target models is constructed to validate the network. All the images are formulated using the electromagnetic simulation tool. Experiments on the dataset reveal their effectiveness. Compared with current methods, superior performance is achieved regarding the target's shape and energy estimation.