首页|基于线性判别分析的海上目标检测算法

基于线性判别分析的海上目标检测算法

扫码查看
传统单一特征检测方法的检测性能较差,通过多特征联合检测方法可以有效提高检测性能.采用多特征联合检测方法在提高性能之外,也会造成计算量增加以及信息冗余.对此提出了一种基于线性判别分析的海上目标检测方法,将单一特征映射到二维特征空间中,形成两组特征组合,RDPH-RVE特征组合和RPH-TEM特征组合,并在二维特征组合基础上进行降维处理.通过将单一特征映射到二维空间中,降低海杂波与目标重叠区域,再通过线性判别分析方法,将雷达回波数据在区分性更好的方向进行投影,在保留信息的同时减少了计算量.
Detection Algorithm of Maritime Target Based on Linear Discriminant Analysis
The detection performance of the traditional single feature method is poor,and the detection perfor-mance can be effectively improved by multi-feature joint detection method.However,the use of multi-feature joint meth-ods will not only improve the detection performance,but also lead to an increase in calculation and information redun-dancy.In this paper,a detection method for floating small targets based on linear discriminant analysis is proposed.The single feature is mapped to a two-dimensional feature space to form two groups of feature combinations,which named RDPH-RVE and RPH-TEM.Dimension reduction is carried out on the basis of two-dimensional feature combination.By mapping a single feature into a two-dimensional space,the overlapping area between sea clutter and the target is re-duced.Then through the linear discriminant analysis method,the radar data is projected in a more distinguishable direc-tion,which reduces the amount of calculation while retaining the information.

feature extractionsmall target detectionsea cluttermulti-feature combination

颜雯丽、丁昊、刘宁波、王中训

展开 >

烟台大学物理与电子信息学院,山东 烟台 264005

海军航空大学,山东 烟台 264001

特征提取 小目标检测 海杂波 多特征联合

2024

雷达科学与技术
中国电子科技集团公司第38研究所 中国电子学会无线电定位技术分会

雷达科学与技术

CSTPCD北大核心
影响因子:0.665
ISSN:1672-2337
年,卷(期):2024.22(6)