Feature Extraction for Target Classification Using an FMCW Radar Sensor

This work presents a preprocessor for classification of FMCW radar signal processing. Since the start position and the speed are different for each target, the classification accuracy can be improved by calibrating the distance and the timing for the target image. Thus, the size and start timing of the echo signal was corrected through the proposed preprocessor. To verify the proposed preprocessor, a hand gesture recognition system environment was built. The performance evaluation results showed that the gesture recognition accuracy for the five gestures was measured to be 91.5% in a user-independent manner.