Principal Component Reconstruction Error for Hyperspectral Anomaly Detection

• Published in: IEEE geoscience and remote sensing letters 2015-08, Vol.12 (8), p.1725-1729
• Main Authors: Jablonski, James A., Bihl, Trevor J., Bauer, Kenneth W.
• Format: Article
• Language: English
• Subjects: Algorithms; Anomaly detection (AD); Detectors; dimensionality reduction (DR); Histograms; hyperspectral imagery (HSI); Hyperspectral imaging; Image reconstruction; object detection; Principal component analysis; principal component analysis (PCA); Principal components analysis; reconstruction error; remote sensing; residual analysis; support vector data description (SVDD)
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2015.2421813

In this letter, a reliable, simple, and intuitive approach for hyperspectral imagery (HSI) anomaly detection (AD) is presented. This method, namely, the global iterative principal component analysis (PCA) reconstruction-error-based anomaly detector (GIPREBAD), examines AD by computing errors (residuals) associated with reconstructing the original image using PCA projections. PCA is a linear transformation and feature extraction process commonly used in HSI and frequently appears in operation prior to any AD task. PCA features represent a projection of the original data into lower-dimensional subspace. An iterative approach is used to mitigate outlier influence on background covariance estimates. GIPREBAD results are provided using receiver-operating-characteristic curves for HSI from the hyperspectral digital imagery collection experiment. Results are compared against the Reed-Xiaoli (RX) algorithm, the linear RX (LRX) algorithm, and the support vector data description (SVDD) algorithm. The results show that the proposed GIPREBAD method performs favorably compared with RX, LRX, and SVDD and is both intuitively and computationally simpler than either RX or SVDD.