Large-area remote sensing image ground object extraction method and system

The invention provides a large-area remote sensing image ground object extraction method and system. The method comprises the following steps: retrieving and downloading required remote sensing image data and digital elevation model data; performing radiometric calibration, atmospheric correction, format conversion and geometric correction on the downloaded image data; integrating an object-oriented image ground object extraction algorithm; performing ground feature extraction operation on the preprocessed remote sensing image through knowledge distillation of sample data and unclassified image object data features; the related remote sensing images are supervised and classified, and an extraction result and a traditional supervised classification extraction result are subjected to precision comparison by using overall precision and a kappa coefficient. According to the large-area remote sensing image ground object extraction method and system provided by the invention, the data distribution difference of mul