基于新型光谱相似度量核的高光谱异常检测算法  

A Novel Spectral Similarity Measurement Kernel Based Anomaly Detection Method in Hyperspectral Imagery

作　　者：梅锋[1] 赵春晖[1] 孙岩 王立国[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院

出　　处：《光子学报》2009年第12期3165-3170,共6页Acta Photonica Sinica

基　　金：国家自然科学基金(60802059);高等学校博士学科点基金(20060217021);黑龙江省自然科学重点基金(ZJG0606-01)资助

摘　　要：提出一种新型光谱相似度量核函数,并应用于高光谱异常检测.由于高斯径向基核函数是基于光谱向量间欧式距离的度量,其对于光谱向量间距离变化的适应性较强,而对于因光照强度变化,阴影和遮挡等引起的同种地物光谱变化的适应性较弱,使得基于高斯径向基核的高光谱异常检测算法性能下降.为解决该问题,从光谱曲线形状描述出发,基于光谱相似度量提出了光谱相似度量核函数.通过理论分析和真实高光谱数据异常检测实验检验,实验结果说明相对于高斯径向基核函数,光谱相似度量核函数具有一定的优越性,能改善基于核方法的高光谱异常检测算法的性能.A novel spectral similarity measurement kernel function is proposed and applied to anomaly detection in hyperspectral imagery. As the Gaussian Radial Basis Function （RBF） is based on the Euclidean distance of two spectral vectors, it is sensitive for distance variations of two spectral vectors, but not for spectral curve variation coming from radiation intensity variation, shadow, shading etc. When the spectral curves of a materials are variety, the detection performance of the RBF based anomaly detectors are degenerate. In order to solve the spectral curves variation problems for the same materials, a spectral similarity measurement kernel function is proposed according to the spectral curves similarity descriptionin in this paper. A theoretical analysis is expounded and numerical experiments are conducted on real hyperspectral imagery. The detection result comparison of Gaussian Radial Basis Function based and Spectral Similarity Measurement Kernel based anomaly detector shows the Spectral Similarity Measurement kernel can improve the performance of kernel base anomaly detection method in hyperspectral imagery.

关 键 词：高光谱 异常检测 光谱相似度量 核方法 RX 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]