以相关系数为特征量的飞机目标识别法

利用各目标距离像之间的相关系数 ,可提高基于距离像建库的目标识别方法的性能。该文提出了利用相关系数构造特征矢量和用神经网络进行分类的雷达目标识别方法。研究了特征矢量的分类性能、最终判决量的确定、相关系数特征矢量法与最大相关系数法各自的特点等问题。对 6类飞机目标全方位角范围的识别结果表明 :最大相关系数法在高信噪比时的识别率较高 ,相关系数特征矢量法的抗噪性较强 ,两种识别方法有较强的互补性。若按某种方式将两者结合起来 ,将得到识别率和抗噪性俱佳的识别方法

Aircraft target recognition using feature correlation coefficients

The correlation coefficients of target range profiles can be used to further improve the performance of the target recognition method based on a range profile database. This paper introduces a new method which first uses the range profile correlation coefficients to construct feature vectors, then classifies the profiles using BP neural networks. The topics studied in this paper include the classification properties of the feature vector, construction of the final decision measure and analysis of the properties of the correlation coefficient feature vector method (CCFVM) and the maximum correlation coefficient method (MCCM). Recognition results for six targets in the whole azimuth range indicated that MCCM has higher recognition rates for high SNR but that CCFVM has excellent anti noise capability and the two methods are highly complementary. Therefore the two methods can be combined to form a method with good recognition rate and anti noise capability.