Hyperspectral channel reduction for local anomaly detection

In this work we propose a novel unsupervised algorithm for designing multispectral filters that are tuned for local anomaly detection algorithms. This problem is formulated as a problem of channel reduction in hyperspectral images, which is performed by replacing subsets of adjacent spectral bands by their means. An optimal partition of hyperspectral bands is obtained by minimizing the Maximum of Mahalanobis Norms (MXMN) of errors, obtained due to misrepresentation of hyperspectral bands by constants. By minimizing the MXMN of errors, one reduces the anomaly contribution to the errors, which allows to retain more anomaly-related information in the reduced channels. We demonstrate that the proposed algorithm produces better results, in terms of the Receiver Operation Characteristic (ROC) curve of a benchmark anomaly detection algorithm (RX) - applied after the dimensionality reduction, as compared to two other dimensionality reduction techniques, including Principal Component Analysis (PCA).