Detecting building boundary using residual U-Net

Suhong Yoo, Jisang Lee, Junsu Bae, Honggyoo Sohn

Research output: Contribution to conferencePaperpeer-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 languageEnglish
Publication statusPublished - 2020
Event40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019 - Daejeon, Korea, Republic of
Duration: 2019 Oct 142019 Oct 18

Conference

Conference40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019
CountryKorea, Republic of
CityDaejeon
Period19/10/1419/10/18

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

Fingerprint Dive into the research topics of 'Detecting building boundary using residual U-Net'. Together they form a unique fingerprint.

Cite this