Generative-adversarial-network-based multi-spectral image change detection method

The invention discloses a generative-adversarial-network-based multi-spectral image change detection method so that problems of low detection precision and high noise sensitive of the existing methodcan be solved. The method comprises: step one, setting structures and objective functions of a discriminant classification network D and a generative network G as well as a distance coefficient lambdabetween the image generated by the generative network G and a real image; step two, acquiring a difference chart ID of images of two different time phases; step three, dividing the ID to obtain an initial change detection result, classifying the two different time phases into marked data and unmarked data based on the result, and forming a training set; step four, forming a classification networkW by the discriminant classification network D and the generative network G, and training the classification network by using the training set to obtain a trained discriminant classification networkD'; and step five, inputting