Research Summaries

Back Automatic Classification of Targets in the Maritime Domain

Fiscal Year 2015
Division Graduate School of Engineering & Applied Science
Department Electrical & Computer Engineering
Investigator(s) Garren, David A.
Sponsor Department of Defense Space (DoD)
Summary Conduct research in specific areas of interest for the sponsor. In particular, the Naval Postgraduate School (NPS) will research advanced processing techniques for the classification of targets in the maritime domain. A primary goal of this research is to determine the viability of classifying certain high-priority targets using electro-optical imagery. It is planned that various features of maritime vessels will be estimated and compared in classifying maritime targets within a hierarchical taxonomy. Such features can include vessel length, width, as well as other structures that can be evident in imagery. It will be important to develop methods for discriminating military vessels from those that are commercial. This work includes the application of analytic methods of advanced signal and image processing based upon realistic signal measurement models for sensors of interest. The resulting analytic equations are transformed into prototype engineering code, such as Matlab. Various resulting algorithms are applied to relevant simulated and measured image data sets in order to determine reliable and robust methods for classifying challenging targets within the maritime domain. This work effort offers to develop a capability for reliable and efficient classification of these challenging targets using available imagery.
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