基于图像处理与时频分析的跳频信号频率估计算法

Frequency Estimation Algorithm of Frequency-hopping Signal Based on Image Processing and Time-frequency Analysis

针对电子侦察领域,复杂电磁环境中跳频信号频率估计的问题,结合图像处理技术提出一种基于时频分析的频率估计算法。首先基于干扰噪声与跳频信号时频特性的差异,通过BM3D与形态滤波的方法对时频图像中含有的高斯白噪声及扫频干扰进行滤除,其次组合采用灰度化、Roberts边缘检测、Hough变换等图像处理手段对信号的时频图像进行处理以突出目标信息,最后通过像素点搜索、阈值处理等方式定位时频脊线的确切位置,估计信号频率。仿真结果表明,该算法能够初步实现信噪比≥-8 dB且在低信噪比条件下保持估计均方误差处于10-5量级范围的信号频率估计,可完成对于低信噪比条件下跳频信号频率的估计。

To solve the problem of frequency estimation of frequency-hopping signal in complex electromagnetic environment in the field of electronic reconnaissance,a frequency estimation algorithm based on time-frequency analysis is proposed in combination with image processing technology.Firstly,based on the differences in time-frequency characteristics between interference noise and frequency-hopping signals,Gaussian white noise and sweeping interference contained in time-frequency images are filtered out using BM3D and morphological filtering methods.Secondly,image processing methods such as grayscale,roberts edge detection and Hough transform are used to process the time-frequency distribution image of the signal to highlight the target information.Finally,the exact position of the time-frequency ridge line is located through pixel search and threshold processing to estimate the signal frequency.The simulation results show that the algorithm can preliminary estimate the signal frequency under the condition of signal-to-noise ratio≥-8 dB,can preliminary maintain the estimation mean square error within the range of 10-5 under low signal-to-noise ratio conditions,.and can estimate the frequency of frequency hopping signals under low signal-to-noise ratio conditions.