红外技术, 2015, 37 (8): 696, 网络出版: 2015-11-30   

基于导弹尾焰特征谱的SVDD 检测方法

A Detection Method Based on Spectrum Characteristics of Missile Plume Using SVDD Algorithm
作者单位
空军工程大学防空反导学院,陕西 西安,710051
摘要
现有天基红外导弹预警系统对目标的探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支持向量数据描述基本理论,提出了一种基于导弹尾焰特征谱的SVDD 检测方法。应用小样本训练数据建立了单分类器,以11 型导弹目标的红外辐射尾焰特征谱数据作为训练样本,比较了RBF 与SSM 作为核函数的检测效果,应用交叉检验的方法确定宽度因子和相似临界因子的值,结果表明,在低信噪比红外图像中,基于SSM-Kernel 的SVDD 检测性能优于基于RBF-Kernel 的检测性能。应用训练样本数据的辐射双峰所对应中心波长作为匹配模板进行识别,实验表明方法具有可行性。
Abstract
The detection of the space-based infrared warning system usually dwells on the infrared images processing. In the paper, a new detection method based on spectral characteristics of ballistic missile plume using SVDD algorithm was discussed, with spectral analytical technology combined with SVDD theory. A one-class classifier was designed under small training set conditions,with the plume infrared spectral characteristics of eleven missile types used as training samples. The effect of detection was compared between RBF kernel function and SSM kernel function and the value of parameter width factor and similar critical factor were decided by cross validation experiment. Experimental results show that SSM-Kernel can obtain satisfactory detection performance than RBF-Kernel in the infrared image with lower Signal Noise Ration. A matching template model was employed applying central wavelength of double radiation peak based on the supported vector sample. Experiments show the method is feasible.

康红霞, 黄树彩, 凌强, 建峰吴, 钟宇. 基于导弹尾焰特征谱的SVDD 检测方法[J]. 红外技术, 2015, 37(8): 696. KANG Hong-xia, HUANG Shu-cai, LING Qiang, WU Jian-feng, ZHONG Yu. A Detection Method Based on Spectrum Characteristics of Missile Plume Using SVDD Algorithm[J]. Infrared Technology, 2015, 37(8): 696.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!