Satellite Image Retrieval Based On Ontology Merging

With the rapid development of remote sensing platform and sensor technique, the amount of satellite images has frequently increased. In order to analyze, manage and retrieve spatial information, several techniques are used to improve the quality of retrieval systems and to perform semantic in the retrieval process. In this paper, we propose an ontology-based approach for semantic retrieving of satellite images, describing the semantic content image and managing uncertain information. The proposed system is composed of three modules: ontological modeling of scene, ontological models merging and semantic retrieval. The first module, describes the semantic image content by an ontological model based on sensor model, scene model and spatial relations model. The second module develops a reliable ontological model of the satellite scene for merging incompletes models and managing uncertain information and conflict situations. The third module retrieves similar satellite images basing on their ontological models retrieves similar satellites images based on their ontological models.