Single-Layer Network Realizes Sparse Aperture ISAR Imaging

doi:10.1109/LGRS.2024.3451305

Single-Layer Network Realizes Sparse Aperture ISAR Imaging

2024-01-01

0

PRE

AI

DOI：10.1109/LGRS.2024.3451305

Original

Original request for help

Save

Abstract

En 中文

Inverse synthetic aperture radar (ISAR) imaging can be compromised by sparse apertures (SAs) leading to diminished image quality. While deep learning models exhibit significant potential for SAs ISAR imaging, existing methods often expand network capacity by stacking layers to enhance imaging outcomes, thereby complicating the training process. Furthermore, the adaptability of the network may be constrained by the fixed computational graph. To address this problem, we propose the ResDEQ model, a novel SAs ISAR imaging method based on a deep equilibrium framework and a single-layer ResNet. ResDEQ decouples the forward and backward propagation processes using fewer parameters, enhancing network flexibility and adaptability to various imaging requirements. Experimental results indicate that ResDEQ surpasses traditional layer-stacked networks in imaging performance.

Keywords:

Imaging

Radar imaging

Mathematical models

Computational modeling

Point cloud compression

Apertures

Backpropagation

Deep equilibrium

deep learning

inverse synthetic aperture radar (ISAR)

sparse aperture (SA) imaging

Single-Layer Network Realizes Sparse Aperture ISAR Imaging

Abstract

Journal

Organization