Monterey, CA; Naval Postgraduate School
IMPROVING AI ALGORITHMS FOR IMAGING SATELLITE OPTICAL ABERRATION ESTIMATION AND CORRECTION
Abstract
dc:description.abstractIn this thesis, artificial intelligence (AI) models for image correction (IC) and wavefront estimation (WE) have been investigated for satellite images corrupted by optical aberrations. Typically, these deep learning algorithms have been trained separately with one algorithm performing IC and another algorithm performing WE. This research aimed to combine previously separate model trainings into one combined model training that optimizes both image correction and wavefront estimation models simultaneously. DeblurGAN IC algorithms, WE algorithms, and the combined wavefront estimation–image correction algorithm (WE-IC) were built, trained, and tested. The combined algorithm’s performance was compared to that of the individual IC and WE algorithms. The combined model yielded superior IC performance to the DeblurGAN models but did not yield definitive improved WE performance. Further research and development of these and similar deep learning algorithms is recommended. Future applications of such algorithms include improved post-processing of satellite images and possibly implementation aboard future satellites and telescopes, offering a cost-effective alternative to implementing traditional active and adaptive optics solutions.
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Astronautical Engineering
- Level thesis:degree_level
- Masters
- Discipline thesis:degree_discipline
- Astronautical Engineering
- Department dc:contributor.department
- Mechanical and Aerospace Engineering (MAE)
- Grantor dc:publisher
- Monterey, CA; Naval Postgraduate School
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bley, Lukas P.
- Advisors dc:contributor.advisor
-
- Agrawal, Brij N.
- Kim, Jae Jun
- Committee member dc:contributor.committeemember
-
- Herrera, Leonardo E.
Rights
dc:rights- Statement dc:rights
-
- This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
- Distribution Statement A. Approved for public release: Distribution is unlimited.
Identifiers
dc:identifier.*- Dc Identifier Programcode
- 591, Space Systems Engineering
- Thesis Thesis Identifier
- 39927