Enhanced Tensor Low-Rank Representation Learning for Hyperspectral Anomaly Detection

Nowadays, some tensor-based hyperspectral anomaly detection (HAD) approaches are still insufficient in utilizing the spatial-spectral structure information of hyperspectral images (HSIs), resulting in the inability to isolate the background and abnormal targets well. In this letter, an enhanced tensor low-rank representation (ETLR) learning model is proposed for HAD. Specifically, the original 3-D HSI data is first decomposed into a structural background component, an anomaly component, and a noise component. Among them, with the help of multisubspace learning technology, the structural background component is reformulated by the t-product of the background dictionary tensor and the corresponding coefficient tensor. Then, the tensor nuclear norm (TNN) is adopted to preserve the global low-rank property of the background component in both spatial and spectral dimensions. For the abnormal component, an l(2,1,1)-norm is designed to enhance the group sparsity of abnormal pixels. For the noise component, a tensor F-norm constraint is imposed to suppress the confusion of noise and anomalies. Meanwhile, a robust dictionary tensor that can adequately characterize the background is constructed by using tensor robust principal component analysis (TRPCA). Furthermore, to reduce the interference of redundant information on detection accuracy, the optimal clustering framework (OCF) method is utilized for band selection. Finally, extensive experiments on one simulated and three real HSI datasets confirm that our algorithm is superior to current HAD algorithms.