Case library construction method using high-resolution remote sensing land cover classification information

Using high-resolution remote sensing images, we propose a case classification method using a land cover classification case library. Case-based reasoning is applied to several aspects of this approach: case representation, case feature selection, case weight, case structure and a similarity measurement model. A detailed study and discussion of the construction of a land cover classification case are presented. Worldview-2 satellite images with 0.5-m spatial resolution are used and the case library construction process for land cover classification information is applied; the effectiveness of the proposed method is then verified using the library. Land cover classification information is thus successfully extracted.