Cargando…

Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers

Preliminary damage assessments (PDA) conducted in the aftermath of a disaster are a key first step in ensuring a resilient recovery. Conventional door-to-door inspection practices are time-consuming and may delay governmental resource allocation. A number of research efforts have proposed frameworks...

Descripción completa

Detalles Bibliográficos
Autores principales: Singh, Deepank Kumar, Hoskere, Vedhus
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10574953/
https://www.ncbi.nlm.nih.gov/pubmed/37837065
http://dx.doi.org/10.3390/s23198235
_version_ 1785120809845522432
author Singh, Deepank Kumar
Hoskere, Vedhus
author_facet Singh, Deepank Kumar
Hoskere, Vedhus
author_sort Singh, Deepank Kumar
collection PubMed
description Preliminary damage assessments (PDA) conducted in the aftermath of a disaster are a key first step in ensuring a resilient recovery. Conventional door-to-door inspection practices are time-consuming and may delay governmental resource allocation. A number of research efforts have proposed frameworks to automate PDA, typically relying on data sources from satellites, unmanned aerial vehicles, or ground vehicles, together with data processing using deep convolutional neural networks. However, before such frameworks can be adopted in practice, the accuracy and fidelity of predictions of damage level at the scale of an entire building must be comparable to human assessments. Towards this goal, we propose a PDA framework leveraging novel ultra-high-resolution aerial (UHRA) images combined with state-of-the-art transformer models to make multi-class damage predictions of entire buildings. We demonstrate that semi-supervised transformer models trained with vast amounts of unlabeled data are able to surpass the accuracy and generalization capabilities of state-of-the-art PDA frameworks. In our series of experiments, we aim to assess the impact of incorporating unlabeled data, as well as the use of different data sources and model architectures. By integrating UHRA images and semi-supervised transformer models, our results suggest that the framework can overcome the significant limitations of satellite imagery and traditional CNN models, leading to more accurate and efficient damage assessments.
format Online
Article
Text
id pubmed-10574953
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-105749532023-10-14 Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers Singh, Deepank Kumar Hoskere, Vedhus Sensors (Basel) Article Preliminary damage assessments (PDA) conducted in the aftermath of a disaster are a key first step in ensuring a resilient recovery. Conventional door-to-door inspection practices are time-consuming and may delay governmental resource allocation. A number of research efforts have proposed frameworks to automate PDA, typically relying on data sources from satellites, unmanned aerial vehicles, or ground vehicles, together with data processing using deep convolutional neural networks. However, before such frameworks can be adopted in practice, the accuracy and fidelity of predictions of damage level at the scale of an entire building must be comparable to human assessments. Towards this goal, we propose a PDA framework leveraging novel ultra-high-resolution aerial (UHRA) images combined with state-of-the-art transformer models to make multi-class damage predictions of entire buildings. We demonstrate that semi-supervised transformer models trained with vast amounts of unlabeled data are able to surpass the accuracy and generalization capabilities of state-of-the-art PDA frameworks. In our series of experiments, we aim to assess the impact of incorporating unlabeled data, as well as the use of different data sources and model architectures. By integrating UHRA images and semi-supervised transformer models, our results suggest that the framework can overcome the significant limitations of satellite imagery and traditional CNN models, leading to more accurate and efficient damage assessments. MDPI 2023-10-03 /pmc/articles/PMC10574953/ /pubmed/37837065 http://dx.doi.org/10.3390/s23198235 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Singh, Deepank Kumar
Hoskere, Vedhus
Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
title Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
title_full Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
title_fullStr Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
title_full_unstemmed Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
title_short Post Disaster Damage Assessment Using Ultra-High-Resolution Aerial Imagery with Semi-Supervised Transformers
title_sort post disaster damage assessment using ultra-high-resolution aerial imagery with semi-supervised transformers
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10574953/
https://www.ncbi.nlm.nih.gov/pubmed/37837065
http://dx.doi.org/10.3390/s23198235
work_keys_str_mv AT singhdeepankkumar postdisasterdamageassessmentusingultrahighresolutionaerialimagerywithsemisupervisedtransformers
AT hoskerevedhus postdisasterdamageassessmentusingultrahighresolutionaerialimagerywithsemisupervisedtransformers