基于非均匀采样数据的HRRP目标识别方法

HRRP target classification and recognition method based on non-uniformly sampled data

针对数据采样率不足或数据缺失条件下的雷达目标识别问题,提出一种基于非均匀采样数据的目标特征提取与识别方法.该方法首先根据数据非均匀采样方式构造与之匹配的稀疏采样矩阵,用以表征目标回波;然后利用稀疏重构算法获取目标高分辨率一维距离像,并从重构结果中提取出包含稀疏特征在内的多维目标特征;最后采用支持向量机实现各种目标的分类.仿真结果表明,该方法能够从非均匀采样数据中有效提取目标特征;所提取的稀疏特征能够克服传统特征目标姿态敏感的问题,显著提高目标识别率.

In order to solve the problem of target recognition caused by insufficient radar sampling rate or missing data, a method of target feature extraction and classification recognition based on non-uniform sampling data is proposed in this paper. Firstly, based on the non-uniform sampling method, the paper constructs the sparse sampling matrix that matches it to represent the target echo, and then uses the sparse reconstruction algorithm to obtain high resolution range profile (HRRP), and extract multi-dimensional target features including sparse features from the reconstruction results. Finally, support vector machine is used to realize the classification of various targets. The simulation results show that the proposed method can effectively extract target features from non-uniformly sampled data, and the extracted sparse features can overcome the pose sensitivity of traditional feature targets, and significantly improve the target recognition rate.