FOD detection based on millimeter wave radar using higher order statistics

Abstract

Weak target detection is one of the key problems facing the foreign object debris (FOD) surveillance radar at the airport runway. A novel FOD detection algorithm based on higher order statistics features and support vector domain description (SVDD) classifier for 77GHz millimeter wave (mm-wave) radar is proposed in this paper. Clutter map constant false alarm rate (CFAR) is firstly applied to the measured data to suppress the heavy background clutter while the FOD returns accompanied by some false alarms are distinguished from the background clutter. Then higher order statistics features are extracted to transform the radar returns into feature domain where FOD and false alarms are more distinguishable. Finally, the one-class SVDD classifier is utilized to accomplish the classification of FOD and false alarms. Experimental results based on measured data show that the proposed method can not only successfully detect FOD but also correctly classify FOD and false alarms.