Classification of Remot Sensing Image Based on Object Oriented and Class Rules

A classification method for remote sensing image based on object oriented and class rules is presented in this paper.The whole image is firstly segmented into image objects and object hierarchy is built using multi-resolution segmentation.Then,the features of objects,such as spectral,geometrical and topological characteristics,are measured.The class rules are constructed based on these features.Classification of remote sensing image is carried out using the rules and information transfering and merging among these objects.The accuracy of the classification approach based on object(oriented) and class rules is checked by a case study of land use classification of Beijing.