Machine learning methods for imaging with applications to space surveillance

Abstract

We have worked for the last five years on low earth orbit satellite imaging with ground-based radar. We focused on distributed and asynchronous ground-based illumination, which requires the use of cross correlations of the data for image formation. The use of such illumination sources has the potential to reduce the cost of the infrastructure needed for space surveillance, but it also has other advantages over conventional matched field imaging methods. One such advantage is that at higher frequencies (K-band and higher), which can provide better resolution, atmospheric inhomogeneities require mitigation. Using correlations is a first step in reducing image blurring and location uncertainty.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 06, 2024
Source ID
FA95502310352

Entities

People

  • George Papanicolaou

Organizations

  • Air Force Office of Scientific Research
  • Stanford University
  • United States Air Force

Tags

Fields of Study

  • Physics

Readers

  • Aerospace Engineering.
  • Atmospheric Remote Sensing.
  • Image Processing and Computer Vision.

Technology Areas

  • AI & ML
  • Space
  • Space - Satellites
  • Space - Space Objects