摘要
随着军事科技的快速发展,现代战场伪装、隐蔽、欺骗、干扰等手段和技术导致的传感器获取的目标识别规律被破坏,针对目标特征逐渐模糊的雷达辐射源识别问题,该文提出了一种基于稀疏表示的辐射源识别方法。该算法首先通过求解一个充分利用信号暂态样本类别信息且可保持样本稀疏表示结构的投影变换来提取低维个体特征矢量;然后通过最大化类间特征的重构误差和最小化类内特征的重构误差来构造目标函数求解投影变换;最后在低维辨别子空间以最小稀疏表示重构误差准则来判定测试样本类别属性。通过仿真实验表明该方法具有较高的识别精度和较强的鲁棒性。
With the rapid development of military technology,the target recognition law of sensor acquisition caused by the means and technology of camouflage,concealment,deception and thousand disturbances in modern battle field is destroyed.Aim⁃ing at the problem of radar emitter recognition with fuzzy target features,a method of emitter recognition based on transient sparse representation is proposed in this paper.The algorithm finds a projection preserved sparse representation structure of transient vec⁃tors and class label information to project the test vector to the optimal low dimensional discriminable subspace.An objective func⁃tion is constructed by simultaneously maximizing reconstructed error of inter-class features,and minimizing reconstructed error of intra-class features.The criterion of minimum reconstruction error of sparse representation for test vector is applied to find classifi⁃cation label.Its applications to signals measured through an antenna show promising results for radiometric identification of emitters in automatic identification system.Simulation shows that the average correct classification ratio of the proposed method has a huge advantage in comparison with the existing algorithm.
作者
刘传波
LIU Chuanbo(No.1 Canglong North Road,Jiangxia Zone of Wuhan,Wuhan 430205)
出处
《舰船电子工程》
2020年第10期72-75,共4页
Ship Electronic Engineering
关键词
雷达辐射源识别
稀疏表示
重构误差
radar emitter recognition
sparse representation
reconstruction error
