光电工程
光電工程
광전공정
OPTO-ELECTRONIC ENGINEERING
2014年
6期
38-44
,共7页
高光谱图像%异常检测%光谱解混%波段子集
高光譜圖像%異常檢測%光譜解混%波段子集
고광보도상%이상검측%광보해혼%파단자집
hyperspectral imagery%anomaly detection%spectral unmixing%bands subsets
由于高光谱图像具有高阶性和背景分布特性复杂的特点,这使得现有的算法在解决异常检测问题时存在一些不足。通过分析高光谱图像的光谱特性和空间特性,基于统计学习理论,利用光谱解混技术和子空间划分方法,提出了基于光谱解混的选择性波段子集高光谱图像异常检测算法。该算法首先利用光谱解混技术提取出对背景分布特性有严重影响的端元光谱,由此降低背景干扰突出异常目标信息;在此基础上,利用子空间划分方法将整个波段空间划分为大小不等的多个子空间,并在每个子空间内利用非高斯程度度量准则提取出富含异常目标信息的特征波段;最后,采用 KRX 算法作为异常检测算子完成异常目标检测。利用真实的高光谱图像对提出的算法进行实验验证,结果表明该算法是有效和合理的,具有良好的异常检测性能。
由于高光譜圖像具有高階性和揹景分佈特性複雜的特點,這使得現有的算法在解決異常檢測問題時存在一些不足。通過分析高光譜圖像的光譜特性和空間特性,基于統計學習理論,利用光譜解混技術和子空間劃分方法,提齣瞭基于光譜解混的選擇性波段子集高光譜圖像異常檢測算法。該算法首先利用光譜解混技術提取齣對揹景分佈特性有嚴重影響的耑元光譜,由此降低揹景榦擾突齣異常目標信息;在此基礎上,利用子空間劃分方法將整箇波段空間劃分為大小不等的多箇子空間,併在每箇子空間內利用非高斯程度度量準則提取齣富含異常目標信息的特徵波段;最後,採用 KRX 算法作為異常檢測算子完成異常目標檢測。利用真實的高光譜圖像對提齣的算法進行實驗驗證,結果錶明該算法是有效和閤理的,具有良好的異常檢測性能。
유우고광보도상구유고계성화배경분포특성복잡적특점,저사득현유적산법재해결이상검측문제시존재일사불족。통과분석고광보도상적광보특성화공간특성,기우통계학습이론,이용광보해혼기술화자공간화분방법,제출료기우광보해혼적선택성파단자집고광보도상이상검측산법。해산법수선이용광보해혼기술제취출대배경분포특성유엄중영향적단원광보,유차강저배경간우돌출이상목표신식;재차기출상,이용자공간화분방법장정개파단공간화분위대소불등적다개자공간,병재매개자공간내이용비고사정도도량준칙제취출부함이상목표신식적특정파단;최후,채용 KRX 산법작위이상검측산자완성이상목표검측。이용진실적고광보도상대제출적산법진행실험험증,결과표명해산법시유효화합리적,구유량호적이상검측성능。
The current anomaly detection algorithms are shortage to solving anomaly detection problem because hyperspectral imagery has a higher order features and complicated background information distribution characteristics. By analyzing the spectral features and the spatial features, and exploiting spectral unmixing and subspace divided methods, based on statistical learning theory, an algorithm of anomaly detection of hyperspectral imagery selectivity band subsets is proposed based on spectral unmixing(UNBS-KRX). At first, hyperspectral imagery reduce the background interference and prominent anomaly target information by using spectral unmixing methods, which extract endmembers spectral, that is great influence on background information distribution of hyperspectral imagery. Then, the algorithm divides the whole bands space to a few subspaces. The size of the subspace is different, and non-Gaussian measurement criterion is used to extract the characteristic bands in each subspace. The bands are rich in anomaly target information. At last, as an anomaly detection operator, the kernel RX completes anomaly target detection. The real hyperspectral data sets are used in the experiments, and the result shows the UNBS-KRX is effective and reasonable, and has an execllent detection performance.