Compound Jamming Detection Technique under High Similarity Background

To address the issue of easy misidentification due to the similarity between suppression jamming and background noise on the time-frequency graph in radar jamming detection, this paper proposes a signal amplitude detection method based on empirically preset thresholds to distinguish them. To address the problem of misidentifying dense false targets and target signals caused by their identical mathematical models and similar features in the time-frequency graph—both appearing as linear shapes with the same tilt angle—we distinguish them by utilizing the evenly spaced distribution pattern of the dense false targets. The simulation results demonstrate that in the compound scenario of suppression jamming and dense false targets jamming, the YOLOv8 model achieves an F1-score of 95.7% for jamming detection. By integrating the outlier rejection module proposed in this paper, this performance can be enhanced to 98.6%.