ijgi-06-00386-v2.pdf (4.12 MB)
Benchmarking the applicability of ontology in geographic object-based image analysis
journal contribution
posted on 2023-05-19, 14:07 authored by Rajbhandari, S, Jagannath Aryal, Jonathan OsbornJonathan Osborn, Musk, R, Arko LucieerArko LucieerIn Geographic Object-based Image Analysis (GEOBIA), identification of image objects is normally achieved using rule-based classification techniques supported by appropriate domain knowledge. However, GEOBIA currently lacks a systematic method to formalise the domain knowledge required for image object identification. Ontology provides a representation vocabulary for characterising domain-specific classes. This study proposes an ontological framework that conceptualises domain knowledge in order to support the application of rule-based classifications. The proposed ontological framework is tested with a landslide case study. The Web Ontology Language (OWL) is used to construct an ontology in the landslide domain. The segmented image objects with extracted features are incorporated into the ontology as instances. The classification rules are written in Semantic Web Rule Language (SWRL) and executed using a semantic reasoner to assign instances to appropriate landslide classes. Machine learning techniques are used to predict new threshold values for feature attributes in the rules. Our framework is compared with published work on landslide detection where ontology was not used for the image classification. Our results demonstrate that a classification derived from the ontological framework accords with non-ontological methods. This study benchmarks the ontological method providing an alternative approach for image classification in the case study of landslides.
History
Publication title
ISPRS International Journal of Geo-InformationVolume
6Article number
386Number
386Pagination
1-24ISSN
2220-9964Department/School
School of Geography, Planning and Spatial SciencesPublisher
M D P I AGPlace of publication
SwitzerlandRights statement
© 2017 by the Authors. Licensed under Creative Commons Attribution 4.0 International (CC BY 4.0) http://creativecommons.org/licenses/by/4.0/Repository Status
- Open