雷达辐射源信号的伪Zernike矩双谱二次特征提取

Radar Emitter Signal Bispectrum Cascade Feature Extraction Based on Pseudo-Zernike Moment

双谱在提取雷达信号特征时可以保留相位信息。针对现有双谱特征提取方法存在平凡双谱、交叉项、特征维数过高等问题,提出一种双谱二次特征提取方法。首先将双谱转化为灰度图像,以灰度值表示双谱幅度;然后利用图像处理技术提取双谱二次特征,提取出能够反映辐射源信号双谱图像细节和概貌信息的不同阶伪Zernike正交矩特征集;最后,将伪Zernike矩特征集与Hu-不变矩特征集进行实验对比。结果表明,文中提出的方法具有更好的分类识别性能。

Bispectrum can retain the phase information when the radar signal features is extracted. Aiming at the problem that bispectrum features based on existing extraction methods contain redundancy bispectrums, cross-items and possess too high feature dimension, a new bispectrum cascade feature extraction method is proposed. Firstly, the bispectrum is converted to gray image and the amplitude of bispectrum is denoted by gray value. Secondly, the bispectrum cascade feature is extracted based on image processing technique. The pseudo-Zernike moment of different orders cascade feature can specify the bispectrum image detail and general information of radar emitter signal. Finally, the comparative experiment is made and it is proved that the pseudo-Zernike moment features is superior to hu-invariant moment features greatly on performing radar signal classification and recognition.