Heritage Conservation and Cultural Preservation

BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING

S. May, A. Dupuis, A. Lagrange, F. De Vieilleville, C. Fernandez-Martin

Published 2022

Thumbnail for BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING
📄 Paper
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.

Abstract

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.

Topics

Predictive Conservation and Risk Assessmentconservation AIdamage detectionmaterial degradation predictionpredictive maintenancerisk modelingsemantic segmentationstructural health monitoring

Cite this paper

@Article{dd46eadb,
AUTHOR = {May, S. and Dupuis, A. and Lagrange, A. and De Vieilleville, F. and Fernandez-Martin, C.},
TITLE = {BUILDING DAMAGE ASSESSMENT WITH DEEP LEARNING},
JOURNAL = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
VOLUME = {XLIII-B3-2022},
YEAR = {2022},
PAGES = {1133--1138},
URL = {https://isprs-archives.copernicus.org/articles/XLIII-B3-2022/1133/2022/},
DOI = {10.5194/isprs-archives-XLIII-B3-2022-1133-2022}
}