DCNN-based dual-temporal remote sensing image change detection method

The invention discloses a DCNN-based dual-temporal remote sensing image change detection method, which comprises the steps of inputting a dual-temporal remote sensing image data set into a deep convolutional neural network to generate a dual-temporal feature map, and performing bilinear interpolation on the dual-temporal feature map; enabling the size of the dual-temporal feature map to be the same as the size of a remote sensing image in the dual-temporal remote sensing image data set, calculating an Euclidean distance between the dual-temporal feature maps after bilinear interpolation, generating a difference image according to the Euclidean distance, extracting a feature vector of each pixel block in the difference image, and constructing a feature vector space according to each featurevector; and clustering the feature vector space, forming the coarse change detection graph according to the clustering result, performing morphological filtering on the coarse change detection graphto generate the change det