Classification of Vehicles with High-Speed Airborne Radar Based on Micro-Doppler Signatures

摘要

With high speed and broad view, airborne radar has a great advantage in moving vehicle tracing, recognition and strike. The high speed also causes complexity in feature extraction of radar echo. In view of this situation, point scatterer models are presented to depicting micro-Doppler effect of vehicle targets, and micro-Doppler signatures are analyzed in time and frequency domain. Also, eigenvalue spectrum is extracted as a feature distinguishing between wheeled vehicles and tracked vehicles, and classification experiments are performed using support vector machine. Experimental results validate the models, and show that the feature extraction method is robust and the classifier is effective.