Research Summaries

Back Exploration of Self-Supervised Learning for SAS Imagery

Fiscal Year 2021
Division Graduate School of Operational & Information Sciences
Department Computer Science
Investigator(s) Orescanin, Marko
Olson, Derek
Sponsor Office of Naval Research (Navy)
Summary Having the ability to automatically identify imaging artifacts in SAS imagery is of the great interest to the mine warfare community and is considered a Future Navy Capability. Present techniques used in evaluating imaging quality of SAS are driven by classical signal processing and have not scaled with the technology progress. SAS imagery is produced at large volumes and is either continuously analyzed for quality and information extraction by operators or stored for latter analysis. Opportunity exists to revisit automation of quality monitoring of SAS imagery in the light of new developments in the artificial intelligence and machine learning communities. The goal of this pilot study is to determine whether the proposed approach is feasible to be applied to SAS imagery at scale.
Keywords
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal