Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar

The information of building features especially in the urban area is very important to support urban management and development. Nevertheless, the automated and transferable detection of building features is still challenging because of variations of the spatial and spectral characteristics to suppo...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohd Shahar, Hanani
Format:	Thesis
Language:	English
Published:	2020
Subjects:	Remote Sensing Geomatics
Online Access:	https://ir.uitm.edu.my/id/eprint/33523/1/33523.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uitm-ir.33523
record_format	uketd_dc
spelling	my-uitm-ir.335232024-05-02T03:09:02Z Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar 2020-08-12 Mohd Shahar, Hanani Remote Sensing Geomatics The information of building features especially in the urban area is very important to support urban management and development. Nevertheless, the automated and transferable detection of building features is still challenging because of variations of the spatial and spectral characteristics to support urban building classification using remote sensing techniques. Most previous studies utilized high-resolution images to discriminate buildings from other land use in the urban area and indeed it involves a high cost to achieve that purpose. Consequently, this study utilized a medium resolution remote sensing image, Sentinel-2 with 10-meter spatial resolution to classified the building in Selangor, Malaysia. In order to obtain a good classification accuracy, the suitable segmentation parameters (scale, shape and compactness) and features selection have been determined and Machine learning (ML) algorithms, namely Support Vector Machine (SVM) and Decision Tree (DT) classifiers have been applied to categorized five different classes which are water, forest, green area, building, and road. The result from these two classifiers was then have been compared and it is obviously showing that the SVM classifier is able to produce 20% better accuracy with 93% and kappa is 0.92. Thus, by enhancing the classification techniques in OBIA, building extraction accuracy using ML algorithms for medium resolution images can be improved and the expenses also can be reduced indirectly. 2020-08 Thesis https://ir.uitm.edu.my/id/eprint/33523/ https://ir.uitm.edu.my/id/eprint/33523/1/33523.pdf text en public degree Universiti Teknologi Mara Perlis Faculty of Architecture, Planning and Surverying
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
topic	Remote Sensing Geomatics
spellingShingle	Remote Sensing Geomatics Mohd Shahar, Hanani Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar
description	The information of building features especially in the urban area is very important to support urban management and development. Nevertheless, the automated and transferable detection of building features is still challenging because of variations of the spatial and spectral characteristics to support urban building classification using remote sensing techniques. Most previous studies utilized high-resolution images to discriminate buildings from other land use in the urban area and indeed it involves a high cost to achieve that purpose. Consequently, this study utilized a medium resolution remote sensing image, Sentinel-2 with 10-meter spatial resolution to classified the building in Selangor, Malaysia. In order to obtain a good classification accuracy, the suitable segmentation parameters (scale, shape and compactness) and features selection have been determined and Machine learning (ML) algorithms, namely Support Vector Machine (SVM) and Decision Tree (DT) classifiers have been applied to categorized five different classes which are water, forest, green area, building, and road. The result from these two classifiers was then have been compared and it is obviously showing that the SVM classifier is able to produce 20% better accuracy with 93% and kappa is 0.92. Thus, by enhancing the classification techniques in OBIA, building extraction accuracy using ML algorithms for medium resolution images can be improved and the expenses also can be reduced indirectly.
format	Thesis
qualification_level	Bachelor degree
author	Mohd Shahar, Hanani
author_facet	Mohd Shahar, Hanani
author_sort	Mohd Shahar, Hanani
title	Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar
title_short	Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar
title_full	Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar
title_fullStr	Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar
title_full_unstemmed	Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar
title_sort	building detection using object-based image analysis (obia) and machine learning (ml) algorithms / hanani mohd shahar
granting_institution	Universiti Teknologi Mara Perlis
granting_department	Faculty of Architecture, Planning and Surverying
publishDate	2020
url	https://ir.uitm.edu.my/id/eprint/33523/1/33523.pdf
_version_	1804889628496363520

Building detection using object-based Image analysis (OBIA) and machine learning (ML) algorithms / Hanani Mohd Shahar

Similar Items