Unlocking Signal Processing With Image Detection: A Frequency Hopping Detection Scheme for Complex EMI Environments Using STFT and CenterNet

Accurate detection and parameter estimation of frequency hopping (FH) signals remain challenging in FH signal-based transmission systems. This study proposes a scheme combining time-frequency analysis (TFA) deep learning (DL)-based image processing algorithms to alleviate the degradation accuracy performance caused by complex electromagnetic interference (EMI). A short-time Fourier transform (STFT) was used obtain signal spectrogram, which reflects energy concentration-dependent manner. Then, CenterNet-based network employed identify each hop’s shape position, reducing computational burden via lightweight neural while maintaining high recognition accuracy. Inverse mapping from coordinates spectrogram perform (TF) domain. The error reduced precisely locating centroid using CenterNet. simulation results demonstrate that proposed can accurately estimate at low signal-to-noise ratio (SNR) with EMI. Furthermore, appropriately determining optimal parameters CenterNet ensure estimator provides novel approach for integrating DL into EMI environments.