Kernel-Based Subpixel Target Detection for Hyperspectral Images  

作　　者：GU Yanfeng LIU Ying ZHANG Ye 

机构地区：[1]Department of Information Engineering, Harbin Institute of Technology, Harbin 150001, China

出　　处：《Chinese Journal of Electronics》2007年第3期485-488,共4页电子学报（英文版）

基　　金：This work is supported in part by the National Natural Science Foundation of China （NSFC） （No.60402025 and No.60472048）, and supported by Development Program for 0utstanding Young Teachers in Harbin Institute of Technology, and Aeronautic Science Foundation.

摘　　要：In this paper, a kernel-based subspace detection algorithm is proposed for hyperspectral subpixel target detection, which combines Kernel principal component analysis （KPCA） with Linear mixture model （LMM）. The LMM is used to describe each pixel as mixture of target, background and noise. The KPCA is used to build background subspace. Finally, a normalized statistical detector maximizing Signal-to-noise （SNR） is used to detect whether each pixel includes target. The algorithm has two merits. First, high order statistics of local regions are exploited to search anomaly regions in order to reduce processing time and improve performance of detection algorithm. Second, the KPCA can better construct subspaces of target and background from nonlinear data. The numerical experiments are performed on AVIRIS data with 126 bands. The experimental results show that the algorithm has good detection performance and good ability to restrain background and can commendably overcome spectral variability of the targets.

关 键 词：Hyperspectral images Target detection Anomaly detection Generalized likelihood ratio test （GLRT） 

分 类 号：TN7[电子电信—电路与系统]