Toward Efficient Hyperspectral Anomaly Detection With Subspace Transformation Learning

Current research in hyperspectral anomaly detection often incorporates low-rank (LR) or total variation (TV) priors to encode the background matrix. However, applying such regularizers to the detection model increases the computational burden. In this letter, we propose a subspace transformation learning-based anomaly detector (termed STLAD). In STLAD, we employ an orthogonal transformation to represent the background in its subspace, where both the background and the transformation share spatial smoothness prior and approximate sparsity properties based on carefully selected basis vectors. By leveraging this background characterization, the anomaly component can be effectively described using the $\ell _{2,1}$ mixed norm. To solve the STLAD model, we design an alternating direction method of multipliers (ADMM) with guaranteed convergence. Experiments conducted on benchmark hyperspectral datasets demonstrate that STLAD outperforms several state-of-the-art anomaly detection methods. The demo of STLAD will be publicly available at https://github.com/XiangfeiShen/STLAD.