| CPC G01S 7/417 (2013.01) [G01S 7/021 (2013.01); G01S 7/4021 (2013.01)] | 17 Claims |

|
1. A method for recognizing a low-probability-of-interception (LPI) radar signal waveform, comprising:
obtaining, by a radar signal receiver, an LPI radar signal s(t), s(t) varying with time t;
extracting, by a radar signal processor, an adaptive feature and a pre-defined analytical feature from the LPI radar signal s(t), wherein the pre-defined analytical feature includes a Wigner-Ville Distribution (WVD) feature, a Choi-William Distribution (CWD) feature, and a wavelet feature;
combining, by the radar signal processor, the adaptive feature with the pre-defined analytical feature to generate a constructed adaptive feature according to:
F=ψ{G1(FAD), G2(FWVD), G3(FCWD), G4(FWL)}, wherein F is the constructed adaptive feature, FAD is the adaptive feature, FWVD is the WVD feature, FCWD is the CWD feature, FWL is the wavelet feature, G1, G2, G3, G4, are linear or non-linear operations, and ψ is a data fusion operation; and
applying, by the radar signal processor, a convolutional neural network (CNN) model to classify the constructed adaptive feature to recognize the LPI radar signal waveform.
|