Computer Vision Methods for Frequency Analysis of RFI in Radio Astronomy Data

Radio Frequency Interference (RFI) increasingly contaminates the radio astronomy spectrum, often exceeding astronomical signal amplitudes by 50-70 dB. Reliable detection and mitigation are therefore essential for studies of faint transient phenomena such as pulsars and fast radio bursts (FRBs). Existing practical methods (including Spectral Kurtosis (SK), Median Absolute Deviation (MAD), and SumThreshold) perform well in many settings but depend on assumptions about the RFI environment and data statistics, limiting their effectiveness for weak, broadband, or non stationary interference. We develop a transform based RFI detection method that requires no prior knowledge of RFI origin or type. Using Green Bank Telescope (GBT) data containing PSR J1713+0747, with 4096 channels spanning 1.1-1.9 GHz and 5.12 micro second sampling, we apply a Short Time Fourier Transform (STFT) to each channel and use an image segmentation algorithm on the STFT magnitude to generate a binary RFI mask. The masked data are inverse transformed and reassembled into a cleaned time series. Performance is assessed using the Signal to Noise Ratio (S/N) of a single pulse of PSR J1713+0747, with SK serving as the baseline. The cleaned spectrogram is dedispersed, integrated across frequency, and evaluated through the resulting S/N. Experimental results show that refining each channel's frequency content via STFT, followed by segmentation in the STFT domain, yields measurable improvements in RFI suppression.