Detecting building boundary using residual U-Net

Suhong Yoo; Jisang Lee; Junsu Bae; Honggyoo Sohn

Detecting building boundary using residual U-Net

Suhong Yoo, Jisang Lee, Junsu Bae, Honggyoo Sohn

Department of Civil and Environmental Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

In order to automatically extract buildings from satellite images, we conducted experiments using Residual U-Net, one of semantic segmentation algorithms. Although limitations have been found, it has the advantage of automatically and quickly acquiring the building information which has been manually extracted by humans in the past.

Original language	English
Publication status	Published - 2020
Event	40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019 - Daejeon, Korea, Republic of Duration: 2019 Oct 14 → 2019 Oct 18

Conference

Conference	40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019
Country/Territory	Korea, Republic of
City	Daejeon
Period	19/10/14 → 19/10/18

Bibliographical note

Funding Information:
This research was supported by a grant (2019-MOIS32-015) of Disaster-Safety Promotion Program funded by Ministry of Interior and Safety (MOIS, Korea).

Publisher Copyright:
© 2020 40th Asian Conference on Remote Sensing, ACRS 2019: "Progress of Remote Sensing Technology for Smart Future". All rights reserved.

All Science Journal Classification (ASJC) codes

Information Systems

Cite this

@conference{d36562563dd0483f86dca1af0999c0e1,

title = "Detecting building boundary using residual U-Net",

abstract = "In order to automatically extract buildings from satellite images, we conducted experiments using Residual U-Net, one of semantic segmentation algorithms. Although limitations have been found, it has the advantage of automatically and quickly acquiring the building information which has been manually extracted by humans in the past.",

author = "Suhong Yoo and Jisang Lee and Junsu Bae and Honggyoo Sohn",

note = "Funding Information: This research was supported by a grant (2019-MOIS32-015) of Disaster-Safety Promotion Program funded by Ministry of Interior and Safety (MOIS, Korea). Publisher Copyright: {\textcopyright} 2020 40th Asian Conference on Remote Sensing, ACRS 2019: {"}Progress of Remote Sensing Technology for Smart Future{"}. All rights reserved.; 40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019 ; Conference date: 14-10-2019 Through 18-10-2019",

year = "2020",

language = "English",

}

TY - CONF

T1 - Detecting building boundary using residual U-Net

AU - Yoo, Suhong

AU - Lee, Jisang

AU - Bae, Junsu

AU - Sohn, Honggyoo

N1 - Funding Information: This research was supported by a grant (2019-MOIS32-015) of Disaster-Safety Promotion Program funded by Ministry of Interior and Safety (MOIS, Korea). Publisher Copyright: © 2020 40th Asian Conference on Remote Sensing, ACRS 2019: "Progress of Remote Sensing Technology for Smart Future". All rights reserved.

PY - 2020

Y1 - 2020

N2 - In order to automatically extract buildings from satellite images, we conducted experiments using Residual U-Net, one of semantic segmentation algorithms. Although limitations have been found, it has the advantage of automatically and quickly acquiring the building information which has been manually extracted by humans in the past.

AB - In order to automatically extract buildings from satellite images, we conducted experiments using Residual U-Net, one of semantic segmentation algorithms. Although limitations have been found, it has the advantage of automatically and quickly acquiring the building information which has been manually extracted by humans in the past.

UR - http://www.scopus.com/inward/record.url?scp=85105831863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85105831863&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85105831863

T2 - 40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019

Y2 - 14 October 2019 through 18 October 2019

ER -

Detecting building boundary using residual U-Net

Abstract

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this