REMOTE-SENSING IMAGE CHANGE DETECTION METHOD BASED ON DEEP CONVOLUTIONAL NETWORK

The present invention relates to the field of change detection. Provided is a remote-sensing image change detection method based on a deep convolutional network. The method comprises: S1, acquiring a previous-time-phase image and later-time-phase image of a target region, and performing preprocessing and data enhancement on the previous-time-phase image and the later-time-phase image; S2, constructing a change detection model and performing pre-training, wherein the change detection model comprises a feature extraction network, a change comparison network and an output network; S3, performing pyramid feature extraction on both the previous-time-phase image and the later-time-phase image by means of the feature extraction network, so as to obtain a first feature and a second feature; S4, inputting the first feature and the second feature into the change comparison network, respectively performing linear mapping on the first feature and the second feature to obtain a first feature vector and a second feature ve