Machine Learning Approaches to Maritime Detection

Detection in the maritime domain requires the radar return from targets to be distinguishable
from the background interference. These radars traditionally use non-coherent processing due
to the time-varying and range-varying nature of the Doppler spectra. However, as radar
platforms fly higher and look down at steeper angles, the sea clutter power will increase and
traditional methods will not be as effective. This talk covers several new approaches for
target detection in the maritime domain. These include the use of sparse signal separation
algorithms, including dictionary learning, two machine learning algorithms and the
application of the single snapshot coherent detector. Each of these techniques is demonstrated
using using either real or realistic simulated sea clutter and shows good potential when
compared to traditional processing methods.

Speaker(s): Luke Rosenberg,

Room: CST 4-201, Bldg: Center of Science & Technology, Syracuse University, 111 College Pl, Syracuse, New York, United States, 13210, Virtual: https://events.vtools.ieee.org/m/402058