论文部分内容阅读
探讨了高分辨率雷达视频回波特征提取及识别方法。鉴于时域视频回波波形特征变化较快，不适合作为目标特征进行识别。回波频域的波形（频谱）相差不大，为了提高谱的分辨率，本文提出对回波信号作Ｃｈｉｒｐ－ｚ变换，以提高谱的分辨率。理论分析与实验结果均表明以回波信号的Ｃｈｉｒｐ－ｚ变换作为目标特征优越性。以ＢＰ网络作为分类器，对两类目标进行了识别，仿真结果说明了此方法的有效性。
The method of feature extraction and identification of high resolution radar video echo is discussed. In view of the time-domain video echo waveform feature changes rapidly, not suitable as a target feature recognition. In order to improve the spectral resolution, we proposed a Chirp-z transform of the echo signal to improve the spectral resolution. Both theoretical analysis and experimental results show that the Chirp-z transform of echo signal is the target feature superiority. Using BP network as a classifier, two types of targets are identified, and the simulation results show the effectiveness of this method.