
handle: 10945/64370
Project Summary: In 2015, a former Naval Postgraduate School (NPS) student postulated that emerging commercial satellite imagery, combined with computer vision (CV), might drastically change the nature of executing maritime domain awareness (MDA). He further surmised that this approach would deliver such detail and depth of data that the patterns of life (POL) for high priority vessels of interest (VOI) could be inferred, leading to predictive analytics. In 2018 we completed our third and final year of MDA research based on the above premise. This paper explains the discoveries, operational implications, and challenges encountered in attempting to prove this hypothesis. This effort included journeys near and far, explorations of many emerging technologies, and lessons learned with implications for longer term MDA. The hypothesis remained constant, always guiding the research whatever the branch we were chasing. Many students and researchers were involved. We found his hypothesis to be technically feasible, yet unachievable due to operational, resource, and organizational reasons. This executive summary explains the hypothesis in detail, a chronological review of the research achievements, and why technical hypothesis validation did not occur. We end with lessons, conclusions, and recommendations.
This research is supported by funding from the Naval Postgraduate School, Naval Research Program (PE0605853N/2098). https://nps.edu/nrp
Approved for public release; distribution is unlimited.
Chief of Naval Operations (CNO)
US Fleet Forces Command (USFF)
NPS NRP Executive Summary
machine learning, non-cooperative vessels of interest, maritime domain awareness, computer vision, UN sanctioned vessels
machine learning, non-cooperative vessels of interest, maritime domain awareness, computer vision, UN sanctioned vessels
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
