Unmixing Component Analysis for Anomaly Detection in Hyperspectral Imagery

Anomaly detection is one of the most important applications for hyperspectral images. In this paper, a new algorithm called unmixing component analysis (UCA) is proposed for anomaly detection in hyperspectral imagery. The proposed algorithm firstly performs spectral unmixing only with background endmembers on original hyperspectral images, and the unmixing error data are retained. Secondly, kernel principal component analysis (KPCA) is performed on the error data to concentrate and extract useful information about anomalous targets. After that, non-linear principal component that includes the most information about anomalous targets is selected based on non-Gaussianity measures. Finally, anomaly detection is conducted on the selected non-linear principal component using RX detector. Numerical experiments are performed on AVIRIS data with 126 bands. The experimental results show the proposed algorithm greatly modifies performance of the conventional RX algorithm and has good detection performance with low false alarms.