HYPERSPECTRAL ANOMALY DETECTION BASED ON ADAPTIVE WEIGHTED SPARSE DICTIONARY LEARNING

The background estimation and modeling are the core of hyperspectral anomaly detection. However, the complex hyperspectral image does not conform to the assumption of multivariate normal distribution in most methods. At the same time, the existence of unknown abnormal targets in the background will also affect the modeling of the background. To solve the above problems, a hyperspectral anomaly detection method based on adaptive weighted sparse dictionary learning (AWSDLD) is proposed in this paper. Firstly, the dictionary learning framework based on adaptive weights is used to learn more representative background dictionaries without considering the background distribution. Secondly, due to the capped norm property, the proposed method can effectively suppress the influence of abnormal targets on background modeling. Finally, the abnormal targets are more significant and easier to be detected in the residual image between the reconstructed image and the original image. The experimental results on three real datasets show the effectiveness of the proposed method.