Du Lan 1 , Li Lin-sen 1 , Li Wei-lu 1 , Wang Bao-shuai 1 , Shi Hui-ruo 1
01 December 2015
Target classification, Feature extraction, Micro-Doppler effect
This paper reports the classification of helicopters, propeller-driven aircraft, and turbojet based on differences in their time-domain modulation periods using a conventional radar system. First, we determine the modulation periods of their time-domain echoes. Then, based on the differences in the time-domain modulation periods, we propose a method for the extraction of time-domain correlation features. Finally, based on the simulated and measured data, via a support vector machine classifier, it is proved that the time-domain correlation features can yield the good classification performance, even with the relatively low pulse repetition frequency, which may induce the ambiguity in Doppler-frequency domain.
This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/