Spectral Feature Learning for Anomaly Change Detection in Hyperspectral Image

Recently, anomaly change detection has attracted considerable interest in hyperspectral image (HSI) analysis. Hyperspectral anomaly change detection (HACD) focuses more on detecting anomalies between multi-temporal hyperspectral images. This paper presents a novel anomaly change detection algorithm that has the following innovations. First, using the variational autoencoder to reconstruct the background of input, forcing its latent features to obey the Gaussian distribution, which can help to reconstruct the background better. Second, in order to obtain a better quality reconstruction of the background map, the spectral angular distance is introduced as a model constraint. Third, impose constraints on the encoder to better learn the background information of the input and improve the reconstruction effect of the network. The proposed algorithm has superior performance over some other algorithms on "Viareggio 2013" datasets.