Semantic reasoning based on object-oriented remote sensing analyzing technology

In the preprocessing course of spatial data, different departments always have diverse naming methods when describing the same geographical entity, due to different backgrounds and views of angle. There are also great differences among the feature sets which are used to describe concepts of geo-ontology, making it difficult to conduct semantic interoperation based on the theory of concepts reasoning in the information science. Consequently, this paper proposes a reasoning method of geo-ontology based on object-oriented remote sensing image analysis by the examples of greenbelt system. The multi-scale segmentation technology of object-oriented remote sensing is used to establish an image hierarchical network system firstly. Then domain ontology system concepts have been mapped to image layers by using maximum area method. Simultaneity, reasoning rules of object information is established via analyzing the features of image objects. And then, semantic interconnection could come true between ontology system concepts and image objects. There are two different images used in this experiment to obtain the same conclusion, which proves the feasibility of this method.