Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images

During disaster response, it is very important to obtain the information of collapsed building distribution accurately and quickly. However, limited by some practical factors, existed methods often suffer from the contradiction between the accuracy and efficiency of building damage extraction. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiayi Ge, Qiao Wang, Hong Tang
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2024.2318357
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846127697098440704
author Jiayi Ge
Qiao Wang
Hong Tang
author_facet Jiayi Ge
Qiao Wang
Hong Tang
author_sort Jiayi Ge
collection DOAJ
description During disaster response, it is very important to obtain the information of collapsed building distribution accurately and quickly. However, limited by some practical factors, existed methods often suffer from the contradiction between the accuracy and efficiency of building damage extraction. This paper proposed a simple and effective framework to rapid recognize collapsed building objects using pre-disaster building distribution maps and post-disaster quasi-panchromatic remote sensing images. The proposed method is validated using several historical disasters in the xBD dataset and tested using three cases of earthquakes in terms of both effectiveness and efficiency. In addition, we have verified that the texture information of optical remote sensing images can be used as the main basis to judge whether a building is collapsed or not, so the panchromatic images are sufficient to enable the deep learning model to correctly recognize collapsed buildings. The experimental results indicate that using quasi-panchromatic images can alleviate the influence of style variations and diverse roof colors present in multi-spectral images on the model’s generalization performance, resulting in an average overall accuracy improvement of 2.4%. Additionally, the reduced data volume leads to an improvement in inference efficiency.
format Article
id doaj-art-d36da4b0093042a0b4b0082d76c4a70d
institution Kabale University
issn 2279-7254
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series European Journal of Remote Sensing
spelling doaj-art-d36da4b0093042a0b4b0082d76c4a70d2024-12-11T11:43:31ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542024-12-0157110.1080/22797254.2024.2318357Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic imagesJiayi Ge0Qiao Wang1Hong Tang2State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing, PR ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing, PR ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing, PR ChinaDuring disaster response, it is very important to obtain the information of collapsed building distribution accurately and quickly. However, limited by some practical factors, existed methods often suffer from the contradiction between the accuracy and efficiency of building damage extraction. This paper proposed a simple and effective framework to rapid recognize collapsed building objects using pre-disaster building distribution maps and post-disaster quasi-panchromatic remote sensing images. The proposed method is validated using several historical disasters in the xBD dataset and tested using three cases of earthquakes in terms of both effectiveness and efficiency. In addition, we have verified that the texture information of optical remote sensing images can be used as the main basis to judge whether a building is collapsed or not, so the panchromatic images are sufficient to enable the deep learning model to correctly recognize collapsed buildings. The experimental results indicate that using quasi-panchromatic images can alleviate the influence of style variations and diverse roof colors present in multi-spectral images on the model’s generalization performance, resulting in an average overall accuracy improvement of 2.4%. Additionally, the reduced data volume leads to an improvement in inference efficiency.https://www.tandfonline.com/doi/10.1080/22797254.2024.2318357Building damageremote sensingobject-leveldisaster responsereal-timedeep learning
spellingShingle Jiayi Ge
Qiao Wang
Hong Tang
Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images
European Journal of Remote Sensing
Building damage
remote sensing
object-level
disaster response
real-time
deep learning
title Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images
title_full Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images
title_fullStr Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images
title_full_unstemmed Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images
title_short Real-time identification of collapsed buildings triggered by natural disasters using a modified object-detection network with quasi-panchromatic images
title_sort real time identification of collapsed buildings triggered by natural disasters using a modified object detection network with quasi panchromatic images
topic Building damage
remote sensing
object-level
disaster response
real-time
deep learning
url https://www.tandfonline.com/doi/10.1080/22797254.2024.2318357
work_keys_str_mv AT jiayige realtimeidentificationofcollapsedbuildingstriggeredbynaturaldisastersusingamodifiedobjectdetectionnetworkwithquasipanchromaticimages
AT qiaowang realtimeidentificationofcollapsedbuildingstriggeredbynaturaldisastersusingamodifiedobjectdetectionnetworkwithquasipanchromaticimages
AT hongtang realtimeidentificationofcollapsedbuildingstriggeredbynaturaldisastersusingamodifiedobjectdetectionnetworkwithquasipanchromaticimages