Hyperspectral anomaly change detection with slow feature analysis

The aim of hyperspectral anomaly change detection is to distinguish the small and anomalous changes from the non-changes and pervasive changes in the multi-temporal hyperspectral remote sensing image scene. The predictor is a very important process to produce the change residual image, in which the spectral differences of the background pixels should be minimized to make the target changes more anomalous and easily separated. Feature extraction is also needed for the residual image, to improve the performance. In this paper, we propose a new hyperspectral anomaly change detection method with slow feature analysis (SFA). SFA is first employed to obtain the change residuals. Several of the top bands of the residual image are then selected as the input of the RX anomaly detection algorithm to detect the anomalous changes. Two sets of experiments using multi-temporal Hyperion imagery prove that the proposed method performs better in detecting anomalous changes than the other state-of-the-art methods.