BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING

Global warming modifies the climate balance. Warming parameters are observed by many Earth Observation satellite systems, and the huge amount of data modifies the way to process them. This paper presents a few studies relative to damage detection on buildings, occurred during natural disasters. Rece...

Full description

Bibliographic Details
Main Authors: S. May, A. Dupuis, A. Lagrange, F. De Vieilleville, C. Fernandez-Martin
Format: Article
Language:English
Published: Copernicus Publications 2022-05-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/1133/2022/isprs-archives-XLIII-B3-2022-1133-2022.pdf
_version_ 1828347949230325760
author S. May
A. Dupuis
A. Lagrange
F. De Vieilleville
C. Fernandez-Martin
author_facet S. May
A. Dupuis
A. Lagrange
F. De Vieilleville
C. Fernandez-Martin
author_sort S. May
collection DOAJ
description Global warming modifies the climate balance. Warming parameters are observed by many Earth Observation satellite systems, and the huge amount of data modifies the way to process them. This paper presents a few studies relative to damage detection on buildings, occurred during natural disasters. Recent advances in deep learning techniques are used for the building detection such as EfficientNet networks. Additional networks as Siamese models are used to evaluate the damage level with pre- and post-event images. Different techniques to merge detection masks are described and compared to a multiclass segmentation network. Results are presented and performances of the different solutions are compared.
first_indexed 2024-04-14T00:47:37Z
format Article
id doaj.art-1133693fa3cc43a2b7521b338bfd4b17
institution Directory Open Access Journal
issn 1682-1750
2194-9034
language English
last_indexed 2024-04-14T00:47:37Z
publishDate 2022-05-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj.art-1133693fa3cc43a2b7521b338bfd4b172022-12-22T02:21:55ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342022-05-01XLIII-B3-20221133113810.5194/isprs-archives-XLIII-B3-2022-1133-2022BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNINGS. May0A. Dupuis1A. Lagrange2F. De Vieilleville3C. Fernandez-Martin4CNES, Toulouse, FranceCNES, Toulouse, FranceAgenium Space, Toulouse, FranceAgenium Space, Toulouse, FranceAgenium Space, Toulouse, FranceGlobal warming modifies the climate balance. Warming parameters are observed by many Earth Observation satellite systems, and the huge amount of data modifies the way to process them. This paper presents a few studies relative to damage detection on buildings, occurred during natural disasters. Recent advances in deep learning techniques are used for the building detection such as EfficientNet networks. Additional networks as Siamese models are used to evaluate the damage level with pre- and post-event images. Different techniques to merge detection masks are described and compared to a multiclass segmentation network. Results are presented and performances of the different solutions are compared.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/1133/2022/isprs-archives-XLIII-B3-2022-1133-2022.pdf
spellingShingle S. May
A. Dupuis
A. Lagrange
F. De Vieilleville
C. Fernandez-Martin
BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
title_full BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
title_fullStr BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
title_full_unstemmed BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
title_short BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
title_sort building damage assessment with deep learning
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/1133/2022/isprs-archives-XLIII-B3-2022-1133-2022.pdf
work_keys_str_mv AT smay buildingdamageassessmentwithdeeplearning
AT adupuis buildingdamageassessmentwithdeeplearning
AT alagrange buildingdamageassessmentwithdeeplearning
AT fdevieilleville buildingdamageassessmentwithdeeplearning
AT cfernandezmartin buildingdamageassessmentwithdeeplearning