Evaluation of a micro-Doppler classification method on mm-wave data

Abstract

Radar micro-Doppler signatures (MDS), which show how different parts of the target move, can be utilized for security and safety applications like detection and assessment of human activity at airports, nuclear power plants etc. We have evaluated a MDS classification method on measured data at 77 GHz. The important part of the method is the feature extraction, which is based on selecting the strongest parts of a Cadence-Velocity Diagram (CVD), which expresses how the curves in the MDS repeat. By our classification of MDSs of human gaits we study also how MDSs of more general target types and activities can be distinguished. We have analyzed and improved the method. The method is sound with good classification results but needs further evaluations and improvements.