Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping
Ontology-driven Geographic Object-Based Image Analysis (O-GEOBIA) contributes to the identification of meaningful objects. In fusing data from multiple sensors, the number of feature variables is increased and object identification becomes a challenging task. We propose a methodological contribution...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/11/5/503 |
id |
doaj-49ee66443e7a47edbf38615ce849538a |
---|---|
record_format |
Article |
spelling |
doaj-49ee66443e7a47edbf38615ce849538a2020-11-24T21:54:42ZengMDPI AGRemote Sensing2072-42922019-03-0111550310.3390/rs11050503rs11050503Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type MappingSachit Rajbhandari0Jagannath Aryal1Jon Osborn2Arko Lucieer3Robert Musk4Discipline of Geography and Spatial Sciences, School of Technology, Environments and Design, College of Sciences and Engineering, University of Tasmania, Private Bag 76, Hobart, Tasmania 7001, AustraliaDiscipline of Geography and Spatial Sciences, School of Technology, Environments and Design, College of Sciences and Engineering, University of Tasmania, Private Bag 76, Hobart, Tasmania 7001, AustraliaDiscipline of Geography and Spatial Sciences, School of Technology, Environments and Design, College of Sciences and Engineering, University of Tasmania, Private Bag 76, Hobart, Tasmania 7001, AustraliaDiscipline of Geography and Spatial Sciences, School of Technology, Environments and Design, College of Sciences and Engineering, University of Tasmania, Private Bag 76, Hobart, Tasmania 7001, AustraliaTimberlands Pacific, Level 1, Cimitiere House, 113-115 Cimitiere Street, Launceston, Tasmania 7250, AustraliaOntology-driven Geographic Object-Based Image Analysis (O-GEOBIA) contributes to the identification of meaningful objects. In fusing data from multiple sensors, the number of feature variables is increased and object identification becomes a challenging task. We propose a methodological contribution that extends feature variable characterisation. This method is illustrated with a case study in forest-type mapping in Tasmania, Australia. Satellite images, airborne LiDAR (Light Detection and Ranging) and expert photo-interpretation data are fused for feature extraction and classification. Two machine learning algorithms, Random Forest and Boruta, are used to identify important and relevant feature variables. A variogram is used to describe textural and spatial features. Different variogram features are used as input for rule-based classifications. The rule-based classifications employ (i) spectral features, (ii) vegetation indices, (iii) LiDAR, and (iv) variogram features, and resulted in overall classification accuracies of 77.06%, 78.90%, 73.39% and 77.06% respectively. Following data fusion, the use of combined feature variables resulted in a higher classification accuracy (81.65%). Using relevant features extracted from the Boruta algorithm, the classification accuracy is further improved (82.57%). The results demonstrate that the use of relevant variogram features together with spectral and LiDAR features resulted in improved classification accuracy.http://www.mdpi.com/2072-4292/11/5/503GEOBIArule-based classificationontologymachine learningrandom forestsrules extractionvariogramsemantic similaritiessemantic variogram |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sachit Rajbhandari Jagannath Aryal Jon Osborn Arko Lucieer Robert Musk |
spellingShingle |
Sachit Rajbhandari Jagannath Aryal Jon Osborn Arko Lucieer Robert Musk Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping Remote Sensing GEOBIA rule-based classification ontology machine learning random forests rules extraction variogram semantic similarities semantic variogram |
author_facet |
Sachit Rajbhandari Jagannath Aryal Jon Osborn Arko Lucieer Robert Musk |
author_sort |
Sachit Rajbhandari |
title |
Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping |
title_short |
Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping |
title_full |
Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping |
title_fullStr |
Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping |
title_full_unstemmed |
Leveraging Machine Learning to Extend Ontology-Driven Geographic Object-Based Image Analysis (O-GEOBIA): A Case Study in Forest-Type Mapping |
title_sort |
leveraging machine learning to extend ontology-driven geographic object-based image analysis (o-geobia): a case study in forest-type mapping |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-03-01 |
description |
Ontology-driven Geographic Object-Based Image Analysis (O-GEOBIA) contributes to the identification of meaningful objects. In fusing data from multiple sensors, the number of feature variables is increased and object identification becomes a challenging task. We propose a methodological contribution that extends feature variable characterisation. This method is illustrated with a case study in forest-type mapping in Tasmania, Australia. Satellite images, airborne LiDAR (Light Detection and Ranging) and expert photo-interpretation data are fused for feature extraction and classification. Two machine learning algorithms, Random Forest and Boruta, are used to identify important and relevant feature variables. A variogram is used to describe textural and spatial features. Different variogram features are used as input for rule-based classifications. The rule-based classifications employ (i) spectral features, (ii) vegetation indices, (iii) LiDAR, and (iv) variogram features, and resulted in overall classification accuracies of 77.06%, 78.90%, 73.39% and 77.06% respectively. Following data fusion, the use of combined feature variables resulted in a higher classification accuracy (81.65%). Using relevant features extracted from the Boruta algorithm, the classification accuracy is further improved (82.57%). The results demonstrate that the use of relevant variogram features together with spectral and LiDAR features resulted in improved classification accuracy. |
topic |
GEOBIA rule-based classification ontology machine learning random forests rules extraction variogram semantic similarities semantic variogram |
url |
http://www.mdpi.com/2072-4292/11/5/503 |
work_keys_str_mv |
AT sachitrajbhandari leveragingmachinelearningtoextendontologydrivengeographicobjectbasedimageanalysisogeobiaacasestudyinforesttypemapping AT jagannatharyal leveragingmachinelearningtoextendontologydrivengeographicobjectbasedimageanalysisogeobiaacasestudyinforesttypemapping AT jonosborn leveragingmachinelearningtoextendontologydrivengeographicobjectbasedimageanalysisogeobiaacasestudyinforesttypemapping AT arkolucieer leveragingmachinelearningtoextendontologydrivengeographicobjectbasedimageanalysisogeobiaacasestudyinforesttypemapping AT robertmusk leveragingmachinelearningtoextendontologydrivengeographicobjectbasedimageanalysisogeobiaacasestudyinforesttypemapping |
_version_ |
1725866337115308032 |