A Framework for Geographic Object-Based Image Analysis (GEOBIA) based on geographic ontology
- 1Key Laboratory of Geo-Informatics of State Bureau of Surveying and Mapping, Chinese Academy of Surveying and Mapping, 28 Lianhuachi Road, P.R. China
- 2School of Geodesy and Geomatics, Wuhan University, Luojiashan, P.R. China
- 3Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, 11 Datunlu, P.R. China
Keywords: Geographic Object-Based Image Analysis, Geographic Ontology, Semantic Network Model, Ontology Web Language
Abstract. GEOBIA (Geographic Object-Based Image Analysis) is not only a hot topic of current remote sensing and geographical research. It is believed to be a paradigm in remote sensing and GIScience. The lack of a systematic approach designed to conceptualize and formalize the class definitions makes GEOBIA a highly subjective and difficult method to reproduce. This paper aims to put forward a framework for GEOBIA based on geographic ontology theory, which could implement "Geographic entities - Image objects - Geographic objects" true reappearance. It consists of three steps, first, geographical entities are described by geographic ontology, second, semantic network model is built based on OWL(ontology web language), at last, geographical objects are classified with decision rule or other classifiers. A case study of farmland ontology was conducted for describing the framework. The strength of this framework is that it provides interpretation strategies and global framework for GEOBIA with the property of objective, overall, universal, universality, etc., which avoids inconsistencies caused by different experts’ experience and provides an objective model for mage analysis.