A Fast Hyperspectral Anomaly Detection Algorithm Based on Greedy Bilateral Smoothing and Extended Multi-Attribute Profile

To address the difficulty of separating background materials from similar associated with use “single-spectral information” for hyperspectral anomaly detection, a fast detection algorithm based on what we term “greedy bilateral smoothing and extended multi-attribute profile” (GBSAED) method is proposed to improve precision operation efficiency. This utilizes smoothing” decompose low-rank part image (HSI) dataset calculate spectral anomalies. process improves operational Then, profile used extract spatial anomalies restrict shape Finally, two components are combined limit false alarms obtain appropriate results. new considers both information an improved structure that ensures Using five real HSI datasets, this study demonstrates GBSAED more robust than eight representative algorithms under diverse application scenarios greatly