基于图像处理的跳频信号参数估计和双网台分选

Parameter Estimation and Dual-Network Station Sorting of Frequency�Hopping Signal Based on Image Processing

针对多网台的跳频信号的参数估计和网台分选问题,提出了使用图像处理的方法。针对低信噪比的情况下参数估计精确率低的问题,提出了适用于图像处理去噪的自适应定门限二分聚类算法。最后,进行了实验仿真,仿真结果表明通过自适应定门限二分聚类算法对跳频信号进行去噪后,再通过图像处理的深度学习检测框架可以有效地对双网台的跳频信号进行网台分选,并且较为精确地识别出跳频参数。

To address the problem of parameter estimation and network station selection of frequency hopping signals from multiple network stations,this paper proposes a method using image processing.An adaptive threshold binary clustering algorithm suitable for image processing denoising is proposed to solve the problem of low accuracy in parameter estimation under low signal-to-noise ratio.Finally,experimental simulation is conducted,and the simulation results indicate that after denoising the frequency hopping signals using the adaptive threshold binary classification clustering algorithm,the deep learning detection framework of image processing can effectively sort the frequency hopping signals of dual network stations and accurately identify the frequency hopping parameters.