基于ACE算法的高光谱隐蔽目标探测  

Hyperspectral concealed target detection based on ACE algorithm

作　　者：张旭辉 卫宏[1] 黄西莹[1] 宋磊[1] 刘培桢[1] 李涛[1] 王姣颖 许开銮[1] 刘轩 王洁[1] ZHANG Xuhui;WEI Hong;HUANG Xiying;SONG Lei;LIU Peizhen;LI Tao;WANG Jiaoying;XU Kailuan;LIU Xuan;WANG Jie(Xi'an Institute of Applied Optics,Xi'an 710065,China)

机构地区：[1]西安应用光学研究所,陕西西安710065

出　　处：《应用光学》2023年第4期801-808,共8页Journal of Applied Optics

摘　　要：隐蔽目标的探测一直都是军事上重点研究的领域,随着高光谱成像技术的发展,为这一领域提供了新的解决思路。利用高光谱数据高的谱间分辨率,可在某些波段实现对隐蔽目标和背景的光谱区分,提出了一种基于ACE(alternation conditional expectations)算法高光谱隐蔽目标探测技术,充分利用背景和隐蔽目标在不同波段光谱不同的特点,引入光谱重排技术和一阶微分技术,使得背景光谱出现振荡,从而提取出目标。相较其他算法,该文提出的算法提取精度高、虚警率低,实现了较好的隐蔽目标探测效果。The detection of concealed targets has always been a focus of military research.With the development of hyperspectral imaging technology,a new solution was provided for this field.By using the high spectral resolution of hyperspectral data,the spectral discrimination of concealed targets and backgrounds could be realized in some wavebands.A hyperspectral concealed target detection technology based on ACE algorithm was proposed,which made full use of the different characteristics of backgrounds and concealed targets in different bands.The spectral rearrangement technology and first-order differential technology were introduced to make the background spectrum oscillate and extract the targets.Compared with other algorithms,the proposed algorithm has higher extraction accuracy and lower false alarm rate,which achieves better detection effect of concealed targets.

关 键 词：隐蔽目标 高光谱 ACE算法 光谱重排 一阶微分 

分 类 号：TN206[电子电信—物理电子学]