A selective kernel PCA algorithm for anomaly detection in hyperspectral imagery

In this paper, a selective kernel principal component analysis algorithm is proposed for anomaly detection in hyperspectral imagery. The proposed algorithm tries to solve the problem brought by high dimensionality of hyperspectral images in anomaly detection. This algorithm firstly performs kernel principal component analysis (KPCA) on the original data to fully mine high-order correlation between spectral bands. Then, high-order statistics in local scene are exploited to define local average singularity (LAS), which is used to measure the singularity of each nonlinear principal component transformed. Based on LAS, one component transformed with maximum singularity is selected after KPCA. Finally, with RX detector, anomaly detection is performed on the component selected. Numerical experiments are conducted on real hyperspectral images collected by AVIRIS. The results prove that the proposed algorithm outperforms the conventional RX algorithm.