A New Deception Jamming Signal Detection Technique Based on YOLOv7
Xuan Zhu, Hao Wu, Fangmin He, Jin Meng · 2023
In order to improve the jamming recognition and anti-jamming capability of cognitive intelligent radar in modern warfare, this paper proposes a radar deception jamming signal detection method based on YOLOv7. Firstly, four typical jamming signals including distance deception jamming (DDJ), dense false target jamming (DFTJ), interrupted sampling and repeating jamming (ISRJ), smart noise jamming (SNJ) and linear frequency modulation (LFM) signal commonly used in radar are obtained by digital signal processing simulation. Then, the LFM and four jamming signals are transformed into time-frequency spectrum by short-time Fourier transform (STFT) to construct the radar jamming signal image dataset. Finally, the YOLOv7 object detection algorithm is used to detect the jamming signals. The experimental results show that the detection accuracy (mAP) of the proposed method is 99.63%, which can accurately detect the radar deception jamming signal.