Research Article
Improved RT-DETR Model for Blind Parameter Estimation of FH Signals Under VLF Interference
@INPROCEEDINGS{10.1007/978-3-032-33662-0_6, author={Qinghua Ying and Tiantian Zhang and Dongyang Xu}, title={Improved RT-DETR Model for Blind Parameter Estimation of FH Signals Under VLF Interference}, proceedings={Communications and Networking. 20th EAI International Conference, ChinaCom 2025, Xi’an, China, November 8--9, 2025, Proceedings}, proceedings_a={CHINACOM}, year={2026}, month={10}, keywords={VLF Communication Frequency Hopping S Transform Deep Learning RT-DETR}, doi={10.1007/978-3-032-33662-0_6} }- Qinghua Ying
Tiantian Zhang
Dongyang Xu
Year: 2026
Improved RT-DETR Model for Blind Parameter Estimation of FH Signals Under VLF Interference
CHINACOM
Springer
DOI: 10.1007/978-3-032-33662-0_6
Abstract
In pervasive Very-Low Frequency (VLF) communication environment, significant challenges arise in the reliable detection and blind parameter estimation of frequency hopping (FH) signals. In this paper, we proposed an improved RT-DETR for blind parameter estimation of FH signals. By deeply identifying the unique characteristics of FH signals in time–frequency (TF) grid and matching it with RMT backbone, we are able to generate a powerful model, named improved RT-DETR to better detect FH signals. To begin, we employ S Transform to generate the TF diagram of the FH signals. Second, based on the diagram, we formulate an improved RT-DETR model which is then utilized for precise parameter estimation of the FH hops. Finally, simulation results show that under the improved RT-DETR model, S Transform is superior to STFT under low signal-to-noise ratios (SNR). Moreover, the improved RT-DETR surpasses YoloV8, YoloV9, and RT-DETR across various SNR, under both S Transform and STFT, indicating the effectiveness of proposed scheme for FH signals and robustness under low SNR and VLF interference.