Artificial intelligence techniques in extracting building and tree footprints using aerial imagery and LiDAR data

Vayghan, SS; Salmani, M; Ghasemkhani, N; Pradhan, B; Alamri, A

Artificial intelligence techniques in extracting building and tree footprints using aerial imagery and LiDAR data

Vayghan, SS Salmani, M Ghasemkhani, N Pradhan, B

Alamri, A

Permalink

Publisher:: TAYLOR & FRANCIS LTD
Publication Type:: Journal Article
Citation:: Geocarto International, 2020
Issue Date:: 2020-01-01

Closed Access

	Filename	Description	Size
	draft_Proof_hi (1)_Symlpetic.pdf	Submitted Manuscript Version	1.87 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Vayghan, SS
dc.contributor.author	Salmani, M
dc.contributor.author	Ghasemkhani, N
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054
dc.contributor.author	Alamri, A
dc.date.accessioned	2021-05-05T01:20:44Z
dc.date.available	2021-05-05T01:20:44Z
dc.date.issued	2020-01-01
dc.identifier.citation	Geocarto International, 2020
dc.identifier.issn	1010-6049
dc.identifier.issn	1752-0762
dc.identifier.uri	http://hdl.handle.net/10453/148675
dc.description.abstract	One of the most important considerations in urban environments is the extraction of urban objects, with a high automation level. This study aims to present a new method which uses aerial images and LiDAR data to extract buildings and trees footprint in urban areas. In this study, high-elevation objects were extracted from the LiDAR data using the developed scan labeling method, and then the classification methods of Neural Networks (NN), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Genetic Based K-Means algorithm (GBKMs) were used to separate buildings and trees and with the purpose of evaluating their performance. The features used for the classification were extracted from aerial images and LiDAR data, and the training data for the classification were selected automatically. Mathematical morphology functions were also used to process the classification results. The results show that NN and the ANFIS are more effective than the genetic-based K-Means algorithm in detecting small and large buildings.
dc.language	English
dc.publisher	TAYLOR & FRANCIS LTD
dc.relation.ispartof	Geocarto International
dc.relation.isbasedon	10.1080/10106049.2020.1844311
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0909 Geomatic Engineering
dc.subject.classification	Geological & Geomatics Engineering
dc.title	Artificial intelligence techniques in extracting building and tree footprints using aerial imagery and LiDAR data
dc.type	Journal Article
utslib.for	0909 Geomatic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAMGIS - Centre for Advanced Modelling and Geospatial lnformation Systems
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Information, Systems and Modelling
utslib.copyright.status	closed_access	*
dc.date.updated	2021-05-05T01:20:42Z
pubs.publication-status	Published

Abstract:

One of the most important considerations in urban environments is the extraction of urban objects, with a high automation level. This study aims to present a new method which uses aerial images and LiDAR data to extract buildings and trees footprint in urban areas. In this study, high-elevation objects were extracted from the LiDAR data using the developed scan labeling method, and then the classification methods of Neural Networks (NN), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Genetic Based K-Means algorithm (GBKMs) were used to separate buildings and trees and with the purpose of evaluating their performance. The features used for the classification were extracted from aerial images and LiDAR data, and the training data for the classification were selected automatically. Mathematical morphology functions were also used to process the classification results. The results show that NN and the ANFIS are more effective than the genetic-based K-Means algorithm in detecting small and large buildings.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/148675