BFGAN-building footprint extraction from satellite images

Yilei Shi, Qingyu Li, Xiao Xiang Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. In this work, we have proposed improved generative adversarial networks (GANs) for the automatic generation of building footprints from satellite images. We used a conditional GAN with a cost function derived from the Wasserstein distance and added a gradient penalty term. The achieved results indicated that the proposed method can significantly improve the quality of building footprint generation compared to conditional generative adversarial networks, the U-Net, and other networks. In addition, our method nearly removes all hyperparameter tuning.

Original languageEnglish
Title of host publication2019 Joint Urban Remote Sensing Event, JURSE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728100098
DOIs
StatePublished - May 2019
Event2019 Joint Urban Remote Sensing Event, JURSE 2019 - Vannes, France
Duration: 22 May 201924 May 2019

Publication series

Name2019 Joint Urban Remote Sensing Event, JURSE 2019

Conference

Conference2019 Joint Urban Remote Sensing Event, JURSE 2019
Country/TerritoryFrance
CityVannes
Period22/05/1924/05/19

Keywords

  • Wasserstein generative adversarial networks (WGANs)
  • building footprint
  • conditional generative adversarial networks (CGANs)
  • generative adversarial networks (GANs)

Fingerprint

Dive into the research topics of 'BFGAN-building footprint extraction from satellite images'. Together they form a unique fingerprint.

Cite this