Generative Models for Monostatic K-Space Enrichment

Abstract

We provide a summary of our investigation regarding K-space augmentation algorithms based on the use of deep generative models for enhancing monostatic radar synthetic aperture imaging. The approach is based on incorporating contextual generative priors into the relevant inverse problem when restricted to a known class of targets. Initial training performance of the generative models as well as efficacy of the proposed contextual generative approach is presented.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 13, 2023
Accession Number
AD1216276

Entities

People

  • Hatim F. Alqadah
  • Matthew J. Burfeindt
  • Raghu G. Raj

Organizations

  • United States Naval Research Laboratory

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computational Science
  • Computers
  • Data Sets
  • Dimensionality Reduction
  • Electromagnetic Scattering
  • Far Field
  • Geometry
  • Information Processing
  • Information Systems
  • Machine Learning
  • Neural Networks
  • Radar Imaging
  • Signal Processing
  • Synthetic Aperture Radar
  • Target Recognition

Readers

  • Organizational Psychology.
  • Radar Systems Engineering.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space
  • Space - Space Objects