Integrating ontological modelling and Bayesian inference for pattern classification in topographic vector data

Abstract

This paper presents an ontology-driven approach for spatial database enrichment in support of map generalisation. Ontology-driven spatial database enrichment is a promising means to provide better transparency, flexibility and reusability in comparison to purely algorithmic approaches. Geographic concepts manifested in spatial patterns are formalised by means of ontologies that are used to trigger appropriate low level pattern recognition techniques. The paper focuses on inference in the presence of vagueness, which is common in definitions of spatial phenomena, and on the influence of the complexity of spatial measures on classification accuracy. The concept of the English terraced house serves as an example to demonstrate how geographic concepts can be modelled in an ontology for spatial database enrichment. Owing to their good integration into ontologies, and their ability to deal with vague definitions, supervised Bayesian inference is used for inferring complex concepts. The approach is validated in experiments using large vector datasets representing buildings of four different cities. We compar classification results obtained with the proposed approach to results produced by a more traditional ontology approach. The proposed approach performed considerably better in comparison to the traditional ontology approach. Besides clarifying the benefits of using ontologies in spatial database enrichment, our research demonstrates that Bayesian networks are a suitable method to integrate vague knowledge about conceptualisations in cartography and GIScience. AbstractThis paper presents an ontology-driven approach for spatial database enrichment in support of map generalisation. Ontology-driven spatial database enrichment is a promising means to provide better transparency, flexibility and reusability in comparison to purely algorithmic approaches. Geographic concepts manifested in spatial patterns are formalised by means of ontologies that are used to trigger appropriate low level pattern recognition techniques. The paper focuses on inference in the presence of vagueness, which is common in definitions of spatial phenomena, and on the influence of the complexity of spatial measures on classification accuracy. The concept of the English terraced house serves as an example to demonstrate how geographic concepts can be modelled in an ontology for spatial database enrichment. Owing to their good integration into ontologies, and their ability to deal with vague definitions, supervised Bayesian inference is used for inferring complex concepts. The approach is validated in experiments using large vector datasets representing buildings of four different cities. We compare classification results obtained with the proposed approach to results produced by a more traditional ontology approach. The proposed approach performed considerably better in comparison to the traditional ontology approach. Besides clarifying the benefits of using ontologies in spatial database enrichment, our research demonstrates that Bayesian ...

Characterization and Detection of Building Patterns in Cartographic Data: Two Algorithms

“…For example, collinear patterns have been extensively investigated (Boffet andRocca Serra, 2001, Christophe andRuas, 2002) in order to simplify and typify building groups. An approach to detect higher-level semantics like terraced house (Lüscher et al, 2009) made use of detected building alignments; the detection approach is however not widely applicable as the buildings in their case was topologically adjacent, which is not commonly the case. Therefore, a more comprehensive view of which building patterns are available, and a generic approach to detect and characterize them are required.…”

Spatial Relations Using High Level Concepts

“…Zhang et al [16] proposed algorithms for detecting align-along-road and unstructured building patterns. Luscher et al [19] demonstrated that higher level semantics, such as terraced house, can be derived from building alignments and other criteria. Haunert [20] proposed a methodology for detecting symmetries in building footprints.…”

Planning with Citizens: Implementation of an e-Planning Platform and Analysis of Research Needs

“…This is necessary, since free form sketching by the user requires the platform to recognize what the user wants to draw and, eventually, provide drawing support. The generation and utilization of ontologies together with Bayesian inference methods may yield a promising approach for such object and context recognition (Alvarado & Davis, 2004;Lüscher, Weibel, & Burghardt, 2009;Yin, Chang, & Forbus, 2010).…”