Database structure for the integration of RS with GIS based on semantic network

The integration of remote sensing (RS) with geographical information system (GIS) is a hotspot in geographical information science. A good database structure is important to the integration of RS with GIS, which should be beneficial to the complete integration of RS with GIS, able to deal with the disagreement between the resolution of remote sensing images and the precision of GIS data, and also helpful to the knowledge discovery and exploitation. In this paper, the database structure storing the spatial data based on semantic network is presented. This database structure has several advantages. Firstly, the spatial data is stored as raster data with space index, so the image processing can be done directly on the GIS data that is stored hierarchically according to the distinguishing precision. Secondly, the simple objects are aggregated into complex ones. Thirdly, because we use the indexing tree to depict the relationship of aggregation and the indexing pictures expressed by 2-D strings to describe the topology structure of the objects, the concepts of surrounding and region are expressed clearly and the semantic content of the landscape can be illustrated well. All the factors that affect the recognition of the objects are depicted in the factor space, which provides a uniform mathematical frame for the fusion of the semantic and non-semantic information. Lastly, the object node, knowledge node and the indexing node are integrated into one node. This feature enhances the ability of system in knowledge expressing, intelligent inference and association. The application shows that this database structure can benefit the interpretation of remote sensing image with the information of GIS.