Optimal Preprocessing for Joint Detection and Classification of Wireless Communication Signals in Congested Spectrum Using Computer Vision Methods

The joint detection and classification of RF signals has been a critical problem in the field of wideband RF spectrum sensing. Recent advancements in deep learning models have revolutionized this field, remarkably through the application of state-of-the-art computer vision algorithms such as YOLO (You Only Look Once) and DETR (Detection Transformer) to the spectrogram images. This paper focuses on optimizing the preprocessing stage to enhance the performance of these computer vision models. Specifically, we investigated the generation of training spectrograms via the classical Short-Time Fourier Transform (STFT) approach, examining four classical STFT parameters: FFT size, window type, window length, and overlapping ratio. Our study aims to maximize the mean average precision (mAP) scores of YOLOv10 models in detecting and classifying various digital modulation signals within a congested spectrum environment. Firstly, our results reveal that additional zero padding in FFT does not enhance detection and classification accuracy and introduces unnecessary computational cost. Secondly, our results indicated that there exists an optimal window size that balances the trade-offs between and the time and frequency resolution, with performance losses of approximately 10% and 30% if the window size is four or eight times off from the optimal. Thirdly, regarding the choice of window functions, the Hamming window yields optimal performance, with non-optimal windows resulting in up to a 10% accuracy loss. Finally, we found a 10% accuracy score performance gap between using 10% and 90% overlap. These findings highlight the potential for significant performance improvements through optimized spectrogram parameters when applying computer vision models to the problem of wideband RF spectrum sensing.

Joint Detection and Classification of Communication and Radar Signals in Congested RF Environments Using YOLOv8

In this paper, we present a comprehensive study on the application of YOLOv8, a state-of-the-art computer vision (CV) model, to the challenging problem of joint detection and classification of signals in a highly dynamic and congested RF environment. Using our synthetic RF datasets, we explored three different scenarios with congested communication and radar signals. In the first study, we applied YOLOv8 to detect and classify multiple digital modulation signals coexisting within a highly congested and dynamic spectral environment with significant overlap in both frequency and time domains. The trained model was able to achieve an impressive mean average precision (mAP) of 0.888 at an IoU threshold of 50%, signifying its robustness against spectral congestion. The second part of our research focuses on the detection and classification of multiple polyphase pulse radar signals, including Frank code and P1 through P4 codes. We were able to successfully train YOLOv8 to deliver a nearly perfect mAP50 score of 0.995 in a densely populated signal environment, further showcasing its capability in radar signal processing. In the last scenario, we demonstrated that the model can also be applied to the multi-target detection problem for continuous-wave radar. The synthetic datasets used in these experiments reflect a realistic mix of communication and radar signals with varying degrees of interference and congestion - a setup that has been overlooked by many past research efforts, which have primarily focused on ML-based classification of digital communication signal modulation schemes. Our study demonstrated the potential of advanced CV models in addressing spectrum sensing challenges in congested and dynamic RF environments involving both communication and radar signals. We hope our findings will spur further collaborative efforts to tackle the complexities of congested RF spectrum environments.