Radar frequency band invariant pedestrian classification

The problem of pedestrian classification by radars with different operating bands is considered. The proposed solutions are based on two observations of relation between Doppler spectrums collected within different frequency bands. According to the first observation the Doppler spectrum obtained from the radars with lower operating frequency is an approximate scaled version of the Doppler spectrum obtained within radar with higher operating frequency. According to the second observation the Doppler spectrum of lower operating frequency is similar to the Doppler spectrum of higher operating frequency at specific aspect angle. Two new approaches are proposed for pedestrian classification based on the observations. The first proposed approach deals with new features called local binary mask. The second approach is based on higher order spectral invariants estimated from the Doppler spectrum. The approaches are tested on real 24 GHz radar measurements and simulated 77 GHz radar measurements and show the robustness to operating frequency of the radar.