Research on Land Use/Cover Classification Based on RS and GIS

Abstract

The investigation of the state of land-use/land- cover (LULC) is very important for daily cadastre supervisory work and it is an important foundation link of land management. It is also an important base of the research of land-use/land-cover change (LUCC), as well as pre-processing of monitoring of forest health and simulation of dynamic evolution of natural vegetation landscape. A land classification system is established in view of the research region and the interrelated LULC standards in this paper, then the edit layers of SPOT 5 HRS images with 3 wave bands are fused using software eCognition 4.0. And then applying the eCognition object-oriented classification method, the precise classification chart of the LULC is obtained through interactive experiments on eCognition 4.0. Thus the LULC map is presented. The map includes six classifications of cultivation, grassland, woodland, aquatic area, construction land, and unused land. So this work has certain significance to the research and development ofRS and GIS further integration.