Anomaly detection for a hyperspectral image by using a selective section principal component analysis algorithm
ZHAO Chunhui,HU Chunmei,SHI Hong (College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)
Regarding the great difficulties created by the high dimensions and large volumes of a hyperspectral image,a new anomaly detection algorithm based on selective section principal component analysis(SSPCA) was introduced.First of all,the algorithm divided the spectral image of high dimensions into subset of low dimensions according to the correlation between spectral bands.Next,it performed PCA on every subset and selected one component with maximum singularity in every subset for KRX based on local average singularity(LAS).Numerical experiments were conducted on real hyperspectral images collected by AVIRIS.The result proves that the proposed algorithm outperformed the other algorithms and obtained a better effect of detection and a lower false alarm rate.
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.