一种典型体目标电磁散射特性分类方法研究  

A classification method study for electromagnetic scattering characteristics of typical volume targets

在线阅读下载全文

作  者:吴春光[1] 张文林 孙宝全 Wu Chunguang;Zhang Wenlin;Sun Baoquan(Unit 92941,PLA,Huludao 125000,China;Beijing Institute of Environmental Characteristics,Beijing 100854,China)

机构地区:[1]中国人民解放军92941部队,葫芦岛125000 [2]北京环境特性研究所,北京100854

出  处:《电子测量技术》2020年第22期77-81,共5页Electronic Measurement Technology

摘  要:针对雷达目标特性研究中目标分类识别需求,因复杂目标散射特性可等效为多类型体目标单元散射特性的合成,进而采用单元目标历程图数据训练神经网络(CNN)的方法,用以完成对平板、二面角、三面角、圆柱、圆形顶帽等5类典型体目标的分类识别。其中设计了基于历程图数据训练CNN方法及流程,构建了典型仿真案例,实现了训练准确率为99%,验证准确率为97%,且在测试集上表现良好。设计方法能够准确完成典型体目标分类识别,为进一步开展复杂目标分类识别研究提供一种新的思路。Aiming at the requirement of target classification and recognition in the research of radar target characteristics, as the scattering characteristics of complex targets can be equivalent to the synthesis of scattering characteristics of the multiple types volume target unit, the method of convolutional neural network(CNN) trained by the process chart data of unit target is used to realize the classification and recognition of five typical volume targets, including flat plate, dihedral angle, trihedral angle, cylinder and circular top hat. The method and process of CNN training based on process chart data are designed, typical simulation cases are constructed, 99% training accuracy and 97% verification accuracy are achieved, and good performance is achieved in the test set. The method designed and adopted is able to accurately classify and recognize typical volume targets, and the study provides a new idea for further research of the classification and recognition of complex targets.

关 键 词:典型体目标 历程图 卷积神经网络 分类识别 

分 类 号:TN955[电子电信—信号与信息处理]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象