Skip to main navigation Skip to search Skip to main content

TVTADMM-Net: An ADMM network based on total variation polarization texture denoising

  • Ziwen Wang*
  • , Xueting Shan
  • , Yiyang Luo
  • , Pucheng Li
  • , Yifan Wu
  • , Han Li
  • *Corresponding author for this work
  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Polarimetric Synthetic Aperture Radar (SAR) system can obtain richer scattering characteristics of ground objects. However, the inherent speckle noise in SAR images severely degrades their quality, and traditional denoising methods are difficult to apply to denoise polarimetric SAR images in complex scenarios, especially the texture details. Therefore, an ADMM network based on total variation (TV) polarization texture denoising is proposed in this paper. It preserves the backscatter coefficient properties of the feature target by "smoothing"the texture details. That is, the TV regularization term is added to the denoising process to construct a polarised texture sparse denoising model.

Original languageEnglish
Title of host publicationIEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331515669
DOIs
Publication statusPublished - 2024
Event2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 - Zhuhai, China
Duration: 22 Nov 202424 Nov 2024

Publication series

NameIEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

Conference

Conference2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
Country/TerritoryChina
CityZhuhai
Period22/11/2424/11/24

Keywords

  • ADMM
  • denoising
  • Polarimetric SAR
  • total variation (TV)

Fingerprint

Dive into the research topics of 'TVTADMM-Net: An ADMM network based on total variation polarization texture denoising'. Together they form a unique fingerprint.

Cite this