Hyperspectral anomaly detection method and system based on capsule differential adversarial network

The invention relates to a hyperspectral anomaly detection method and system based on a capsule differential adversarial network. The method comprises the following steps: acquiring a hyperspectral image to be detected; inputting the to-be-measured hyperspectral image into a pre-trained generative adversarial network to obtain a reconstructed image corresponding to the to-be-measured hyperspectral image and the abnormal probability of each pixel point in the reconstructed image; obtaining the generative adversarial network based on training of a background sample training set, where the generative adversarial network comprises a generator and a discriminator which are cascaded, the generator is used for generating reconstructed image data similar to input image data distribution, and the discriminator is used for judging whether the input data is true or false, and the generator and the discriminator are both of a one-dimensional capsule network structure. According to the method of the invention, the pre-tra