最小二乘向量机结合光谱维信息检测弱小目标

doi:10.3969/j.issn.1009-086x.2018.04.014

现代防御技术 ›› 2018, Vol. 46 ›› Issue (4): 86-91.DOI: 10.3969/j.issn.1009-086x.2018.04.014

最小二乘向量机结合光谱维信息检测弱小目标

康红霞, 黄树彩, 黄文龙, 吴建峰

空军工程大学防空反导学院,陕西西安 710051

收稿日期:2017-11-22 修回日期:2018-01-12 出版日期:2018-08-30 发布日期:2020-11-25
作者简介:康红霞(1980-),女,陕西榆林人。讲师,博士生,主要从事空天信息处理技术研究。通信地址:710051 陕西省西安市长乐东路甲字1号空军工程大学防空反导学院 E-mail:supermap1999@163.com。
基金资助:
航空科学基金(20151996015);中国博士后科学基金(2015M572778)

Detection Algorithm for Small and Weak Target Based on LSSVM Combining Spectral Dimension Information

KANG Hong-xia, HUANG Shu-cai, HUANG Wen-long, WU Jian-feng

AFEU,Air and Missile Defense College,Shaanxi Xi'an 710051,China

Received:2017-11-22 Revised:2018-01-12 Online:2018-08-30 Published:2020-11-25

摘要/Abstract

摘要： 现有天基红外导弹预警系统对目标的检测侧重于对红外图像的处理。从光谱维数据分析角度出发,结合红外弱小目标图像信噪比低的特点,提出了一种利用最小二乘向量机(LSSVM)结合目标光谱维信息检测弱小目标的方法,并以F测度函数为适应度函数,利用人工蜂群算法(ABC)对最小二乘向量机的正则化参数和核函数参数进行优化。应用小样本训练数据建立了LSSVM检测器,以4型典型导弹目标尾焰红外辐射特征谱数据作为训练样本,比较了ABC算法、网格搜索(grid search)算法、粒子群(PSO)算法和遗传(GA)算法。实验结果表明,在低信噪比条件下,由ABC优化的LSSVM模型能获得更好的检测性能。

关键词: 红外弱小目标, 导弹尾焰, 最小二乘支持向量机, 参数优化, 人工蜂群算法, 目标检测

Abstract: The detection of the space-based infrared warning system usually dwells on the infrared images processing. A new detection method based on least squares support vector machine (LSSVM) combining spectral dimension information is discussed by analyzing the spectral dimension data and the low signal to noise ratio. Artificial bee colony algorithm is used to optimize the kernel function and regularization parameters, using F measure function as the fitness value. A LSSVM classifier is designed under small training set conditions, using the plume infrared spectrum of four typical missile types as training samples. The detection effect shows that the model of artificial bee colony algorithm optimization achieves better results compared with grid search algorithm, particle swarm optimization and genetic algorithm especially under low signal to noise ratio.

Key words: infrared dim and small targets, missile plume, least squares support vector machine, parameter optimization, artificial bee colony algorithm, target detection

中图分类号:

TJ76
TN215

康红霞, 黄树彩, 黄文龙, 吴建峰. 最小二乘向量机结合光谱维信息检测弱小目标[J]. 现代防御技术, 2018, 46(4): 86-91.

KANG Hong-xia, HUANG Shu-cai, HUANG Wen-long, WU Jian-feng. Detection Algorithm for Small and Weak Target Based on LSSVM Combining Spectral Dimension Information[J]. Modern Defense Technology, 2018, 46(4): 86-91.

参考文献

[1] 黄树彩,凌强,韦道知,等.红外多光谱图像弹道导弹目标检测算法[J].国防科技大学学报,2016,38(6):142-147.
HUANG Shu-cai,LING Qiang,WEI Dao-zhi,et al.Ballistic Target Detection in Infrared Multispectral Imagery[J].Journal of National University of Defense Technology,2016,38(6):142-147.
[2] 苑智玮,黄树彩,熊志刚,等.尾焰特征光谱在主动段弹道目标识别中的应用[J].光学学报,2017,37(2):298-305.
YUAN Zhi-wei,HUANG Shu-cai,XIONG Zhi-gang,et al.Application of Characteristic Plume Spectra in Recognition of Boost Phase Ballistic Target[J].Acta Optica Sinica,2017,37(2):298-305.
[3] 苑智玮,黄树彩,熊志刚,等.基于SVM后验概率的红外弱小目标检测[J].激光与红外,2016,46(6):766-771.
YUAN Zhi-wei,HUANG Shu-cai,XIONG Zhi-gang,et al.Infrared Small Target Detection Based on SVM Posterior Probability[J].Laser & Infrared,2016,46(6):766-771.
[4] 陈炳文,王文伟,秦前清.Fuzzy-ART背景抑制的单帧红外弱小目标检测[J].计算机辅助设计与图形学学报,2012,24(6):775-779.
CHEN Bing-wen,WANG Wen-wei,QIN Qian-qing.Infrared Dim Target Detection in Single Image Based on Background Suppression by Fuzzy-ART [J].Journal of Computer-Aided Design & Computer Graphics,2012,24(6):775-779.
[5] Heather C Vough,Brianna Barker Caza.Where Do I Go from Here? Sensemaking and the Construction of Growth-Based Stories in the Wake of Denied Promotions[J].Acad Manage REV,2017,42(1):103-128.
[6] MANOLAKIS D.Signal Processing Algorithms for Hyperspectral Remote Sensing of Chemical Plumes[C]//IEEE International Conference on Acoustics,2008:1857-1860.
[7] 郭德阳,陈建文,吴瑕.弹道目标尾焰特性探究[J].雷达科学与技术,2014,12(1):106-111.
GUO De-yang,CHEN Jian-wen,WU Xia.Research on Characteristics of Tail Plume of Ballistic Target[J].Radar Science and Technology,2014,12(1):106-111.
[8] Andreas Blanc,Lukas Deimling,Norbert Eisenreich.Uv- and Ir-Signatures of Rocket Plumes[J].Propellants,Explosives,Pyrotechnics,2002,27(3):185-189.
[9] THOMPSON S.American Institute of Aeronautics and Astronautics[J].The Aeronautical Journal,2010,114(1152):122-122.
[10] 康红霞,黄树彩,凌强,等.基于导弹尾焰特征谱的SVDD检测方法[J].红外技术,2015,37(8):696-700.
KANG Hong-xia,HUANG Shu-cai,LING Qiang,et al.A Detection Method Based on Spectrum Characteristics of Missile Plume Using SVDD Algorithm[J].Infrared Technology,2015,37(8):696-700.
[11] 张鑫,郭宜忠,万新敏,等.基于红外特性的弹道导弹助推段预警探测能力仿真[J].舰船电子对抗,2010,33(5):92-95.
ZHANG Xin,GUO Yi-zhong,WAN Xin-min,et al.Simulation of Early Warning and Detection Capability of Ballistic Missile in Boosting Phase Based on Infrared Characteristic[J].Shipboard Electronic Countermeasure,2010,33(5):92-95.
[12] 刘尊洋,邵立,汪亚夫,等.复燃对固体火箭尾焰红外辐射特性的影响[J].光学学报,2013,33(6):40-47.
LIU Zun-yang,SHAO Li,WANG Ya-fu,et al.Influence on Afterburning on Infrared Radiation of Solid Rocket Exhaust Plume[J].Acta Optica Sinica,2013,33(6):40-47.[13] 刘尊洋,汪亚夫,邵立,等.数值模拟液体火箭尾焰流场和红外辐射特性[J].弹箭与制导学报,2013,33(4):119-122.
LIU Zun-yang,WANG Ya-fu,SHAO Li,et al.Numeric Simulation of Flow Field and Infrared Radiation of Liquid Rocket[J].Journal of Projectiles,Rockets,Missiles and Guidance,2013,33(4):119-122.
[14] 张术坤,蔡静,杨永军.尾焰红外辐射特性的反向蒙特卡罗法模拟[J].红外与激光工程,2012,41(10):2604-2609.
ZHANG Shu-kun,CAI Jing,YANG Yong-jun.Simulation of Infrared Radiation Characteristics of the Exhaust Plume by Using Backward Monte Carlo Method[J].Infrared and Laser Engineering,2012,41(10):2604-2609.
[15] 杨灵,方中华,陈桂林.弹道导弹尾焰红外探测性能的大气影响分析[J].应用光学,2008,29(1):52-56.
YANG Ling,FANG Zhong-hua,CHEN Gui-lin.Atmospheric Influence on Infrared Detection Performance of Ballistic Missile Plume[J].Journal of Applied Optics,2008,29(1):52-56.

最小二乘向量机结合光谱维信息检测弱小目标

Detection Algorithm for Small and Weak Target Based on LSSVM Combining Spectral Dimension Information

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李洋, 梁潇, 贾海萨. 基于知识蒸馏的SAR图像舰船目标检测[J]. 现代防御技术, 2023, 51(4): 78-85.
[2]	何明, 朱梓涵, 翟绪龙, 翟政, 郝程鹏. 基于多分支上下文融合的空对地目标检测算法[J]. 现代防御技术, 2023, 51(3): 91-98.
[3]	岳磊, 袁建虎, 杨柳, 吕婷婷. 一种巡逻执勤目标检测算法研究[J]. 现代防御技术, 2023, 51(1): 67-74.
[4]	代妍, 刘丹, 胡庆荣, 陈成增, 王悦循. 一种针对雷达回波分裂的相位补偿处理方法[J]. 现代防御技术, 2022, 50(3): 84-89.
[5]	刘海涵, 吕卫祥. 基于时间反转变换的动目标相参积累算法[J]. 现代防御技术, 2022, 50(2): 67-75.
[6]	刘克, 潘广煜, 郑大国, 顾佼佼, 孟春英. 一种RetinaNet与SE融合的航空取证目标检测算法[J]. 现代防御技术, 2022, 50(1): 25-32.
[7]	李方俊, 王生捷. 伺服系统速度环控制器参数的自整定及优化[J]. 现代防御技术, 2022, 50(1): 102-108.
[8]	李潇飞, 唐意东. 基于先验稀疏模型的光谱图像压缩采样检测[J]. 现代防御技术, 2021, 49(3): 115-122.
[9]	王文庆, 庞颖, 刘洋, 杨东方, 张萌. 双重注意机制的空对地目标智能检测算法[J]. 现代防御技术, 2020, 48(6): 81-88.
[10]	王志虎, 沈小青, 桂伟龙. 光学成像小目标检测技术综述[J]. 现代防御技术, 2020, 48(5): 67-73.
[11]	陈睿容, 孙武, 贾学振, 徐秋锋. 基于二阶Keystone的空间目标检测方法[J]. 现代防御技术, 2020, 48(4): 93-101.
[12]	陈奕琪. 改进群智能算法多目标干扰决策[J]. 现代防御技术, 2020, 48(1): 107-112.
[13]	王万田, 袁俊泉, 王力宝, 陈阿磊. 基于MDCFT的天空双基地雷达机动目标检测方法[J]. 现代防御技术, 2018, 46(3): 191-198.
[14]	张宏伟, 许道明, 马俊涛, 冉宏远. Radon变换的雷达低慢小目标检测方法[J]. 现代防御技术, 2018, 46(3): 105-111.
[15]	许道明, 张宏伟. 雷达低慢小目标检测技术综述[J]. 现代防御技术, 2018, 46(1): 148-155.