loading page

THz imaging enhancement based on Noise2Noise algorithm
  • +1
  • Tianhe Wang,
  • Xuejun Huang,
  • Jinshan Ding,
  • Yuhong Zhang
Tianhe Wang
Xidian University

Corresponding Author:wangtianhe1992@126.com

Author Profile
Xuejun Huang
Xidan University School of Electronic Engineering
Author Profile
Jinshan Ding
Xidian University
Author Profile
Yuhong Zhang
Xidian University
Author Profile

Abstract

Terahertz (THz) imaging has an outstanding advantage of high resolution due to the high frequency and has promising potential in VideoSAR. However, limited to the THz source power and the air absorption, the THz image usually has a low SNR and is susceptible to noise in remote sensing and imaging. In order to improve the quality of THz images, a THz image enhancement method is proposed based on the noise2noise idea. The THz images are reconstructed with the AFBP algorithm. They are organized as noisy image pairs and filtered with a mask to remove the influence of moving targets. Then, the Noise2Noise network is constructed based on the CNN network and takes the noisy image pair as input and reference. In the training stage, 1000 noisy image pairs are used as the training set and 100 noisy images are used as the test set to verify the performance of the proposed method. The experimental results based on real VideoSAR data demonstrate that the proposed method is capable of suppressing noise and enhancing the THz image.
26 Aug 2022Submitted to Electronics Letters
27 Aug 2022Submission Checks Completed
27 Aug 2022Assigned to Editor
31 Aug 2022Reviewer(s) Assigned
24 Jan 2023Review(s) Completed, Editorial Evaluation Pending
24 Jan 2023Editorial Decision: Revise Minor
05 Feb 20231st Revision Received
05 Feb 2023Submission Checks Completed
05 Feb 2023Assigned to Editor
05 Feb 2023Review(s) Completed, Editorial Evaluation Pending
06 Feb 2023Editorial Decision: Accept