loading page

Data-driven sampling pattern design for sparse spotlight SAR imaging
  • +2
  • Yao Zhao,
  • Wenkun Huang,
  • Xiangyin Quan,
  • Bingo Ling,
  • Zhe Zhang
Yao Zhao
Guangdong University of Technology

Corresponding Author:[email protected]

Author Profile
Wenkun Huang
Guangdong University of Technology
Author Profile
Xiangyin Quan
China Academy of Launch Vehicle Technology
Author Profile
Bingo Ling
Guangdong University of Technology
Author Profile
Zhe Zhang
Aerospace Information Research Institute, Chinese Academy of Sciences
Author Profile

Abstract

This paper proposes a joint optimization method for the imaging algorithm and sampling scheme of sparse spotlight syhthetic aperture radar (SAR) imaging based on deep convolutional neural networks. Traditional compressed sensing (CS) based sparse SAR imaging has been widely studied. Deep learning and sparse unfolding networks have been introduced into sparse SAR imaging, but most current works focus only on the imaging stage and simply adopt the conventional uniform or random down-sampling scheme. Considering that the imaging quality also depends on the sampling pattern besides the imaging algorithm, this paper introduces a learning-based strategy to jointly optimize the sampling scheme and the imaging network parameters of the reconstruction module. In a deep learning-based image reconstruction scheme, joint and continuous optimization of the sampling patterns and convolutional neural network parameters is achieved to improve the image quality. Simulation results based on real SAR image dataset illustrate the effectiveness and superiority of the proposed framework.
05 Aug 2022Submitted to Electronics Letters
05 Aug 2022Submission Checks Completed
05 Aug 2022Assigned to Editor
16 Aug 2022Reviewer(s) Assigned
02 Sep 2022Review(s) Completed, Editorial Evaluation Pending
06 Sep 2022Editorial Decision: Revise Minor
18 Sep 20221st Revision Received
19 Sep 2022Submission Checks Completed
19 Sep 2022Assigned to Editor
19 Sep 2022Review(s) Completed, Editorial Evaluation Pending
27 Sep 2022Editorial Decision: Accept
Nov 2022Published in Electronics Letters volume 58 issue 24 on pages 920-923. 10.1049/ell2.12650