|本期目录/Table of Contents|

[1]周 颖,张兴敢*,王 琼. 雷达目标识别算法性能优化与评估系统[J].南京大学学报(自然科学),2017,53(6):1187.[doi:10.13232/j.cnki.jnju.2017.06.021]
 Zhou Ying,Zhang Xinggan*,Wang Qiong. Performance optimization and evaluation system for radar target recognition algorithm[J].Journal of Nanjing University(Natural Sciences),2017,53(6):1187.[doi:10.13232/j.cnki.jnju.2017.06.021]
点击复制

 雷达目标识别算法性能优化与评估系统()
     

《南京大学学报(自然科学)》[ISSN:0469-5097/CN:32-1169/N]

卷:
53
期数:
2017年第6期
页码:
1187
栏目:
出版日期:
2017-12-01

文章信息/Info

Title:
 Performance optimization and evaluation system for radar target recognition algorithm
作者:
 周 颖张兴敢*王 琼
 南京大学电子科学与工程学院,南京,210023
Author(s):
 Zhou YingZhang Xinggan*Wang Qiong
 School of Electronic Science and Engineering,Nanjing University,Nanjing,210023,China
关键词:
 目标识别QtMATLAB混合编程MySQL
Keywords:
 target recognitionQtMATLABmixed programmingMySQL
分类号:
TP181
DOI:
10.13232/j.cnki.jnju.2017.06.021
文献标志码:
A
摘要:
 雷达回波信息量少,目标种类多,给雷达目标识别带来了困难.对不同种类目标,要用不同的特征组合和分类方法,才能得到比较正确的目标识别结果.研究设计了一种使用Qt与MATLAB混合编程的雷达目标识别算法性能优化与评估系统.在MySQL数据库的开发支持环境下建立目标识别算法规则库,使用Qt搭建系统框架和实现前台人机交互,使用MATLAB实现后台数据的计算处理和算法的评估与优化,实现了Qt关于MySQL驱动QMYSQL的编译和Qt通过引擎调用MATLAB的关键技术.整个系统以面向对象的技术和模块化设计思想进行设计,集成了数据导入、后台数据计算处理、识别规则管理、新识别方法输入等功能,为解决不同特征类型的智能化识别问题提供了有效的研究平台,使用方便,具有广泛的应用前景.
Abstract:
 Radar target recognition has always been a hotspot in radar and signal processing,wherein the used data and techniques depend heavily on the scenario.For different kinds of targets,different combinations of characteristics and classification methods are needed in order to make target recognition results more accurate.Radar target recognition technology research not only involves complex algorithms,but also is a very experimental system engineering.A system ofperformance optimization and evaluation for radar target recognition algorithms is designed in this paper.The system is designed on Qt and MATLAB platform.The former is used to build the system framework and realize the foreground man-machine interaction.The latter is used to realize the calculation and optimization of background data.Andthe target recognition algorithm rule database is established on the MySQL database development support environment.Object-oriented technology and modular design ideasare adopted.At the same time,security,reliability,openness and scalability are taken into account in the design phase.In this system,data importing,calculation and processing are excuted in the background,and multiple functions are intergrated,which including mangement of recognition rules,importing of new recognition methods and other functional modules.The target feature data is imported through the foreground man-machine interaction,and according to the selected computing mode,the specific feature transformation algorithm and recognition algorithm are adopted during the phase of training,testing or identifying.According to the specific requirements of the application,the recognition algorithms are selected manually,as well as the recommended rules are stored on the database automatically.And the system is convenient to add the input feature type and recognition algorithm.The system ofperformance optimization and evaluation for radar target recognition algorithms is convenient to use.It provides an effective research platformto solve the intelligent identification problem of different feature types,and has wide application prospects.

参考文献/References:

 [1] 李 明.雷达目标识别技术研究进展及发展趋势分析.现代雷达,2010,32(10):1-8.(Li M.Research progress and development trend analysis on radar target recognition technique.Modern Radar,2010,32(10):1-8.)
[2] Wagner S A.SAR ATR by a combination of convolutional neural network and support vector machines.IEEE Transactions on Aerospace and Electronic Systems,2016,52(6):2861-2872.
[3] Haumtratz T,Worms J,Schiller J.Classification of air targets including a rejection stage for unknown targets.In:2010 11th International Radar Symposium.Vilnius,Republic of Lithuania:IEEE,2010,78(1):1-4.
[4] Bieker T.Statistical evaluation of decision-level fusion methods for non-cooperative target identification by radar signatures.In:2008 11th International Conference on Information Fusion.Cologne,Germany:IEEE,2008:1-7.
[5] Jacobs S P,O’Sullivan J A.Automatic target recognition using sequences of high resolution radar range-profiles.IEEE Transactions on Aerospace and Electronic Systems,2000,36(2):364-381.
[6] De Wit J J M,Harmanny R I A,Molchanov P.Radar micro-Doppler feature extraction using the singular value decomposition.In:Proceedings of the 2014 International Radar Conference(Radar).Lille,France:IEEE,2014:1-6.
[7] Molchanov P,Egiazarian K,Astola J,et al.Classification of aircraft using micro-Doppler bicoherence-based features.IEEE Transactions on Aerospace and Electronic Systems,2014,50(2):1455-1467.
[8] 陈未未,张兴敢.基于一维距离像和微动特征的弹道导弹识别方法.南京大学学报(自然科学),2016,52(6):1113-1120.(Chen W W,Zhang X G.A recognition method of ballistic missile based on multiple feature combination.Journal of Nanjing University(Natural Sciences),2016,52(6):1113-1120.)
[9] Rosenbach K,Schiller J.Identification of aircraft on the basis of 2-D radar images.In:Record of the IEEE International Radar Conference.Alexandria,VA,USA:IEEE,1995,50(10):405-409.
[10] 张兴敢.逆合成孔径雷达成像及目标识别.博士学位论文.南京:南京航空航天大学,2001.(Zhang X G.ISAR imaging and targets recognition.Ph D Dissertation.Nanjing:Nanjing University of Aeronautics and Astronautics,2001.)
[11] Chen S Z,Wang H P.SAR target recognition based on deep learning.In:2014 International Conference on Data Science and Advanced Analytics.Shanghai,China:IEEE,2015:541-547.
[12] 耿 杰,范剑超,初佳兰等.基于深度协同稀疏编码网络的海洋浮筏SAR图像目标识别.自动化学报,2016,42(4):593-604.(Geng J,Fan J C,Chu J L,et al.Research on marine floating raft aquaculture SAR image target recognition based on deep collaborative sparse coding network.Acta Automatica Sinica,2016,42(4):593-604.)
[13] Schumacher R,Schiller J.Non-cooperative target identification of battlefield targets—classification results based on SAR images.In:Proceedings of the 2005 IEEE International Radar Conference.Arlington,VA,USA:IEEE,2005:167-172.
[14] Chen S Z,Wang H P,Xu F,et al.Target classification using the deep convolutional networks for SAR images.IEEE Transactions on Geoscience and Remote Sensing,2016,54(8):4806-4817.
[15] 周志华.机器学习.北京:清华大学出版社,2016,1-13.(Zhou Z H.Machine learning.Beijing:Tsinghua University Press,2016,1-13.)
[16] 魏 鑫,陈辉强,高 飞.Qt与MATLAB的混合编程研究与实现.计算机与现代化,2010,(9):168-170.(Wei X,Chen H Q,Gao F.Research and implementation of mixed-language programming based on Qt and MATLAB.Computer and Modernization,2010,(9):168-170.)

相似文献/References:

备注/Memo

备注/Memo:
 基金项目:江苏省基础研究计划(BK20151391)
收稿日期:2017-06-06
*通讯联系人,E-mail:zhxg@nju.edu.cn
更新日期/Last Update: 2017-11-28