On Two Stages for Refined Building Roof Extraction in an Aerial Image

David Tien, Xiao Yi, Tony Hope

Research output: Book chapter/Published conference paperConference paper

2 Citations (Scopus)
61 Downloads (Pure)

Abstract

Robust segmentation of building roofs is desired in urban and regional planning and asset management. In this paper, we present a two-stage method for building roof region extracting using the cues of colour and edges. At the first stage, three layers are generated. The first and second layer locate initial buildingroof regions by the colour based segmentation processes at two different threshold values to obtain an under-segmentation and an over-segmentation result, respectively. The third layer divides the whole area of the aerial image into pieces by an edge detector. At the second stage, we refine the regions of located building roofs using a combination of regions found in the three layers. Experimental results show that the proposed approach yields intuitively correct as well as accurate extraction of the building roof regions in urban aerial images.
Original languageEnglish
Title of host publication4th ICITA 2007
EditorsShi Guanfan
Place of PublicationSydney, Australia
PublisherMacquarie Scientific Press
Pages1-4
Number of pages4
ISBN (Electronic)9780980326703
Publication statusPublished - 2007
EventInternational Conference on Information Technology and Applications (ICITA) - Harbin, China, China
Duration: 15 Jan 200718 Jan 2007

Conference

ConferenceInternational Conference on Information Technology and Applications (ICITA)
CountryChina
Period15/01/0718/01/07

Fingerprint

Roofs
Antennas
Regional planning
Color
Urban planning
Asset management
Detectors

Cite this

Tien, D., Yi, X., & Hope, T. (2007). On Two Stages for Refined Building Roof Extraction in an Aerial Image. In S. Guanfan (Ed.), 4th ICITA 2007 (pp. 1-4). Sydney, Australia: Macquarie Scientific Press.
Tien, David ; Yi, Xiao ; Hope, Tony. / On Two Stages for Refined Building Roof Extraction in an Aerial Image. 4th ICITA 2007. editor / Shi Guanfan. Sydney, Australia : Macquarie Scientific Press, 2007. pp. 1-4
@inproceedings{556cefad757a49e1b64431a88f1ca315,
title = "On Two Stages for Refined Building Roof Extraction in an Aerial Image",
abstract = "Robust segmentation of building roofs is desired in urban and regional planning and asset management. In this paper, we present a two-stage method for building roof region extracting using the cues of colour and edges. At the first stage, three layers are generated. The first and second layer locate initial buildingroof regions by the colour based segmentation processes at two different threshold values to obtain an under-segmentation and an over-segmentation result, respectively. The third layer divides the whole area of the aerial image into pieces by an edge detector. At the second stage, we refine the regions of located building roofs using a combination of regions found in the three layers. Experimental results show that the proposed approach yields intuitively correct as well as accurate extraction of the building roof regions in urban aerial images.",
keywords = "Open access version available, Building extraction, Image processing, Segmentation",
author = "David Tien and Xiao Yi and Tony Hope",
note = "Imported on 03 May 2017 - DigiTool details were: publisher = Sydney, Australia: Macquarie Scientific Press, 2007. editor/s (773b) = Professor Shi Guanfan; Event dates (773o) = 15-18 Jan 2007; Parent title (773t) = International Conference on Information Technology and Applications (ICITA).",
year = "2007",
language = "English",
pages = "1--4",
editor = "Shi Guanfan",
booktitle = "4th ICITA 2007",
publisher = "Macquarie Scientific Press",

}

Tien, D, Yi, X & Hope, T 2007, On Two Stages for Refined Building Roof Extraction in an Aerial Image. in S Guanfan (ed.), 4th ICITA 2007. Macquarie Scientific Press, Sydney, Australia, pp. 1-4, International Conference on Information Technology and Applications (ICITA), China, 15/01/07.

On Two Stages for Refined Building Roof Extraction in an Aerial Image. / Tien, David; Yi, Xiao; Hope, Tony.

4th ICITA 2007. ed. / Shi Guanfan. Sydney, Australia : Macquarie Scientific Press, 2007. p. 1-4.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - On Two Stages for Refined Building Roof Extraction in an Aerial Image

AU - Tien, David

AU - Yi, Xiao

AU - Hope, Tony

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = Sydney, Australia: Macquarie Scientific Press, 2007. editor/s (773b) = Professor Shi Guanfan; Event dates (773o) = 15-18 Jan 2007; Parent title (773t) = International Conference on Information Technology and Applications (ICITA).

PY - 2007

Y1 - 2007

N2 - Robust segmentation of building roofs is desired in urban and regional planning and asset management. In this paper, we present a two-stage method for building roof region extracting using the cues of colour and edges. At the first stage, three layers are generated. The first and second layer locate initial buildingroof regions by the colour based segmentation processes at two different threshold values to obtain an under-segmentation and an over-segmentation result, respectively. The third layer divides the whole area of the aerial image into pieces by an edge detector. At the second stage, we refine the regions of located building roofs using a combination of regions found in the three layers. Experimental results show that the proposed approach yields intuitively correct as well as accurate extraction of the building roof regions in urban aerial images.

AB - Robust segmentation of building roofs is desired in urban and regional planning and asset management. In this paper, we present a two-stage method for building roof region extracting using the cues of colour and edges. At the first stage, three layers are generated. The first and second layer locate initial buildingroof regions by the colour based segmentation processes at two different threshold values to obtain an under-segmentation and an over-segmentation result, respectively. The third layer divides the whole area of the aerial image into pieces by an edge detector. At the second stage, we refine the regions of located building roofs using a combination of regions found in the three layers. Experimental results show that the proposed approach yields intuitively correct as well as accurate extraction of the building roof regions in urban aerial images.

KW - Open access version available

KW - Building extraction

KW - Image processing

KW - Segmentation

M3 - Conference paper

SP - 1

EP - 4

BT - 4th ICITA 2007

A2 - Guanfan, Shi

PB - Macquarie Scientific Press

CY - Sydney, Australia

ER -

Tien D, Yi X, Hope T. On Two Stages for Refined Building Roof Extraction in an Aerial Image. In Guanfan S, editor, 4th ICITA 2007. Sydney, Australia: Macquarie Scientific Press. 2007. p. 1-4