基于时频能量谱纹理特征的跳频调制方式识别

Frequency hopping modulation recognition based on time-frequency energy spectrum texture feature

针对跳频通信调制方式识别问题,提出了一种基于时频能量谱纹理特征的跳频调制方式识别方法。该方法首先采用平滑伪Wigner-Ville分布算法获取跳频信号时频图,并经过二维维纳滤波去除时频图背景噪声,提高低信噪比条件下时频图清晰度;然后采用连通域检测算法提取每跳信号的时频能量谱并将其转化为时频灰度图,计算其直方图统计特征和灰度共生矩阵特征组成22维特征向量;最后通过参数优化后的支持向量机分类器对特征集进行训练、分类和识别。仿真实验表明,所提取的多维特征向量具有较强的表征能力,避免了由单一特征相似性引起的误判问题,在信噪比为-4dB的条件下,对跳频信号BPSK、QPSK、SDPSK、QASK、64QAM和GMSK共6种调制方式的平均识别正确率达到91.4%。

For frequency hopping modulation identification,a novel method based on time-frequency energy spectrum texture feature was proposed.Firstly,the time-frequency diagram of the frequency hopping signal was obtained by smoothed pseudo Wigner-Ville distribution,and the background noise of the time-frequency diagram was removed by two-dimensional Wiener filtering to improve the resolution of the time-frequency diagram under low SNR conditions. Then,the connected-domain detection algorithm was used to extract the time-frequency energy spectrum of each hop signal and convert it into a time-frequency gray-scale image.The histogram statistical features and the gray-scale co-occurrence matrix feature were combined to form a 22-dimensional eigenvector.Finally,the feature set was trained, classified and identified by optimized support vector machine classifier.Simulation experiments show that the multi- dimensional feature vector extracted by the algorithm has strong representation ability and avoids the misjudgment caused by the similarity of single features.The average recognition accuracy of the six modulation methods of frequency hopping signals BPSK,QPSK,SDPSK,QASK,64QAM and GMSK is 91.4% under the condition of -4 dB SNR.