Dismount feature extraction from circular synthetic aperture radar data

Recently, the use of micro-Doppler radar signatures for classification has become an area of focus, in particular for the case of dynamic targets where many components are interacting over time. One specific target of interest is the dismount. Dismount detection, feature extraction, and classification offers some unique challenges. For instance, humans have small radar cross-sections and slow range-rates making discrimination from clutter difficult. Extracted features may be utilized to distinguish dismounts from other objects, however. In this paper, range-Doppler radar data collected from an airborne circular synthetic aperture radar is analyzed to determine extractable dismount characteristics. The results are compared against high signal-to-clutter ratio results.
^{1 2}