Frequency Hopping Signal Sorting of UAV Based on Image Noise Reduction Technology
Meng Han, Xiaolin Zhang, Yang Li · 2022
Aiming at the limitations of the prior art in the sorting of frequency hopping signals under the condition of low signal-to-noise ratio, this paper proposes a method to reduce the noise of the image through image preprocessing, and then improve different signal-to-noise ratios through neural network sorting. A method for sorting performance of frequency hopping signals is described below. This method first extracts the joint time-frequency map of the frequency hopping signal based on STFT&SPWVD under different signal-to-noise ratios, and then passes through Wiener filtering, gray threshold method and morphological filtering to denoise the image, and then sends it to the neural network for processing. Training, testing, and sorting of frequency hopping signals. The simulation results show that in the range of the signal-to-noise ratio of -20dB to -5dB, the signal can be sorted accurately after denoising the image by the image processing method.