Skip to main navigation Skip to search Skip to main content

SAR Pixelwise Registration via Multiscale Coherent Point Drift With Iterative Residual Map Minimization

  • Qiuze Yu
  • , Pengjie Wu
  • , Dawen Ni*
  • , Haibo Hu
  • , Zhen Lei
  • , Jiachun An
  • , Wen Chen
  • *Corresponding author for this work
  • Shanghai Inst Spaceflight Control Technol

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Due to the severe speckle noise and complex local deformation in synthetic aperture radar (SAR) images, robust pixelwise registration with high accuracy is an important problem but is far from being resolved. The core of this problem is how to establish a precise deformation field that maps every pixel to its corresponding pixel with high accuracy. To address this problem, a novel SAR dense-matching algorithm, which includes high-accuracy landmark generation and a precise deformation field parameter estimation, is proposed in this article. First, a strategy for generating enough well-distributed landmarks is proposed by designing patch matching of improved scale-invariant feature transform features based on phase correlation and the gradient method. Furthermore, a multiscale coherent point drift (MCPD), powered by iterative residual map minimization, is designed to reliably match landmarks and estimate precise field parameters. Both simulated deformed SAR images and real SAR images are utilized to evaluate the performance of the proposed method, and the experimental results demonstrate that the proposed method provides better registration performance than previous methods in terms of both accuracy and robustness.
Original languageEnglish
Article number5200919
Number of pages19
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume60
DOIs
StatePublished - Jan 2022

Funding

This work was supported in part by the National Defense Innovation Science Foundation, in part by the National Natural Science Foundation of China under Grant 61174196, in part by the Innovation Foundation of Equipment Development Department and CASIC, in part by the Innovation Fund of the Shanghai Academy of Spaceflight Technology under Grant SAST2017-080, in part by the Fundamental Research Funds for the Central Universities under Grant 2042019kf0220, and in part by the Open Project Program Foundation of the Key Laboratory of Opto-Electronics Information Processing, Chinese Academy of Sciences under Grant OEIP-O-202009. (Corresponding author: Dawen Ni.)

Keywords

  • Strain
  • Radar polarimetry
  • Synthetic aperture radar
  • Estimation
  • Minimization
  • Feature extraction
  • Speckle
  • Deformation field
  • landmarks
  • pixelwise registration
  • residual map minimization
  • synthetic aperture radar (SAR) image

Indexed by

  • SCIE
  • Scopus
  • EI

Fingerprint

Dive into the research topics of 'SAR Pixelwise Registration via Multiscale Coherent Point Drift With Iterative Residual Map Minimization'. Together they form a unique fingerprint.

Cite this