Improved Threshold-free Automatic Dependent Surveillance-Broadcast preamble detection algorithm based on deep learning framework

In the study of Automatic Dependent Surveillance-Broadcast (ADS-B) signal decoding in S-mode, accurate detection of the signal preamble is a critical prerequisite for successful decoding. To address the challenges of low detection accuracy and slow processing speed in low Signal-to-Noise Ratio (SNR) environments, we propose an intelligent ADS-B signal preamble detection algorithm. First, an improved You Only Look Once version 8 (YOLOv8) object detection model is utilized to precisely capture the ADS-B signal Preamble in the frequency domain. Next, a coordinate transformation method is employed to obtain the temporal position of the preamble pulses within the time domain signal. Finally, an enhanced threshold-free cross-correlation preamble detection algorithm is applied to achieve precise preamble detection in the time domain. Experimental results demonstrate that, in both simulated datasets and real-world measurement environments, the proposed algorithm effectively mitigates the issue of preamble detection accuracy degradation caused by threshold fluctuations under low-SNR conditions. Specifically, the proposed algorithm achieves detection accuracies of 58.7% and 99.8% at SNR = -3 dB and 15 dB, respectively, surpassing traditional detection algorithms in accuracy.