摘要
雷达高分辨距离像(highresolutionrangeprofile,HRRP)具有方位敏感性、平移敏感性以及在特征空间高度交叠的特点,采用复合特征可以更好地描述目标特性。利用复合特征,结合分层识别结构提出了一种分层特征选择方法,充分利用了特征信息,简化了识别器结构,使识别运算量大大下降且提高了识别率。基于HRRP的平移不变特征和相关矢量机的计算机仿真实验表明,该方法是有效的。
Radar high resolution range profile (HRRP) is sensitive to the target aspect and time-shift variation, and highly overlapped in feature space between different targets, which determines that hybrid features are suitable to represent the target's property. Based on hybrid features, a multi-stage feature selection and classification scheme is proposed, which utilizes the feature information more efficiently, decreases the computational complexity and improves the classification performance as well. The simulation results based on relevance vector machine (RVM) classifier show the efficiency of the proposed method.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2005年第4期596-599,695,共5页
Systems Engineering and Electronics
基金
国家自然科学基金 (60 3 0 2 0 0 9)
国防预研项目基金 (4 13 0 70 5 0 1)资助课题
关键词
雷达自动目标识别
高分辨距离像
特征选择
相关矢量机
automatic radar target recognition
high resolution range profile
feature selection
relevance vector machine