InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images

<p dir="ltr">In February 2023, Turkey experienced a series of earthquakes that caused significant damage to buildings and affected many people. Detecting building damage quickly is crucial for helping earthquake victims, and we believe machine learning models offer a promising soluti...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Burak Tasci (17032302) (author)
مؤلفون آخرون: Madhav R. Acharya (17032305) (author), Mehmet Baygin (17032308) (author), Sengul Dogan (16677969) (author), Turker Tuncer (16677966) (author), Samir Brahim Belhaouari (9427347) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513560116199424
author Burak Tasci (17032302)
author2 Madhav R. Acharya (17032305)
Mehmet Baygin (17032308)
Sengul Dogan (16677969)
Turker Tuncer (16677966)
Samir Brahim Belhaouari (9427347)
author2_role author
author
author
author
author
author_facet Burak Tasci (17032302)
Madhav R. Acharya (17032305)
Mehmet Baygin (17032308)
Sengul Dogan (16677969)
Turker Tuncer (16677966)
Samir Brahim Belhaouari (9427347)
author_role author
dc.creator.none.fl_str_mv Burak Tasci (17032302)
Madhav R. Acharya (17032305)
Mehmet Baygin (17032308)
Sengul Dogan (16677969)
Turker Tuncer (16677966)
Samir Brahim Belhaouari (9427347)
dc.date.none.fl_str_mv 2023-09-12T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.jag.2023.103483
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/InCR_Inception_and_concatenation_residual_block-based_deep_learning_network_for_damaged_building_detection_using_remote_sensing_images/24188301
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Earth sciences
Physical geography and environmental geoscience
Engineering
Geomatic engineering
Information and computing sciences
Machine learning
InCR CNN
Earthquake
Building damage detection
Deep feature engineering
INCA
dc.title.none.fl_str_mv InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">In February 2023, Turkey experienced a series of earthquakes that caused significant damage to buildings and affected many people. Detecting building damage quickly is crucial for helping earthquake victims, and we believe machine learning models offer a promising solution. In our research, we introduce a new, lightweight deep-learning model capable of accurately classifying damaged buildings in remote-sensing datasets.</p><p dir="ltr">Our main goal is to create an automated damage detection system using a novel deep-learning model. We started by collecting a new dataset with two categories: damaged and undamaged buildings. Then, we developed a unique convolutional neural network (CNN) called the inception and concatenation residual (InCR) deep learning network, which incorporates concatenation-based residual blocks and inception blocks to improve performance.</p><p dir="ltr">We trained our InCR model on the newly collected dataset and used it to extract features from images using global average pooling. To refine these features and select the most informative ones, we applied iterative neighborhood component analysis (INCA). Finally, we classified the refined features using commonly used shallow classifiers.</p><p dir="ltr">To evaluate ur method, we used tenfold cross-validation (10-fold CV) with eight classifiers. The results showed that all classifiers achieved classification accuracies higher than 98 %. This demonstrates that our proposed InCR model is a viable option for CNNs and can be used to create an accurate automated damage detection application.</p><p dir="ltr">Our research presents a unique solution to the challenge of automated damage detection after earthquakes, showing promising results that highlight the potential of our approach.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Applied Earth Observation and Geoinformation<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jag.2023.103483" target="_blank">https://dx.doi.org/10.1016/j.jag.2023.103483</a></p>
eu_rights_str_mv openAccess
id Manara2_31fc670f5c7930f6e9888a890a5a72df
identifier_str_mv 10.1016/j.jag.2023.103483
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24188301
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing imagesBurak Tasci (17032302)Madhav R. Acharya (17032305)Mehmet Baygin (17032308)Sengul Dogan (16677969)Turker Tuncer (16677966)Samir Brahim Belhaouari (9427347)Earth sciencesPhysical geography and environmental geoscienceEngineeringGeomatic engineeringInformation and computing sciencesMachine learningInCR CNNEarthquakeBuilding damage detectionDeep feature engineeringINCA<p dir="ltr">In February 2023, Turkey experienced a series of earthquakes that caused significant damage to buildings and affected many people. Detecting building damage quickly is crucial for helping earthquake victims, and we believe machine learning models offer a promising solution. In our research, we introduce a new, lightweight deep-learning model capable of accurately classifying damaged buildings in remote-sensing datasets.</p><p dir="ltr">Our main goal is to create an automated damage detection system using a novel deep-learning model. We started by collecting a new dataset with two categories: damaged and undamaged buildings. Then, we developed a unique convolutional neural network (CNN) called the inception and concatenation residual (InCR) deep learning network, which incorporates concatenation-based residual blocks and inception blocks to improve performance.</p><p dir="ltr">We trained our InCR model on the newly collected dataset and used it to extract features from images using global average pooling. To refine these features and select the most informative ones, we applied iterative neighborhood component analysis (INCA). Finally, we classified the refined features using commonly used shallow classifiers.</p><p dir="ltr">To evaluate ur method, we used tenfold cross-validation (10-fold CV) with eight classifiers. The results showed that all classifiers achieved classification accuracies higher than 98 %. This demonstrates that our proposed InCR model is a viable option for CNNs and can be used to create an accurate automated damage detection application.</p><p dir="ltr">Our research presents a unique solution to the challenge of automated damage detection after earthquakes, showing promising results that highlight the potential of our approach.</p><h2>Other Information</h2><p dir="ltr">Published in: International Journal of Applied Earth Observation and Geoinformation<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jag.2023.103483" target="_blank">https://dx.doi.org/10.1016/j.jag.2023.103483</a></p>2023-09-12T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.jag.2023.103483https://figshare.com/articles/journal_contribution/InCR_Inception_and_concatenation_residual_block-based_deep_learning_network_for_damaged_building_detection_using_remote_sensing_images/24188301CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/241883012023-09-12T00:00:00Z
spellingShingle InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
Burak Tasci (17032302)
Earth sciences
Physical geography and environmental geoscience
Engineering
Geomatic engineering
Information and computing sciences
Machine learning
InCR CNN
Earthquake
Building damage detection
Deep feature engineering
INCA
status_str publishedVersion
title InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
title_full InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
title_fullStr InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
title_full_unstemmed InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
title_short InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
title_sort InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images
topic Earth sciences
Physical geography and environmental geoscience
Engineering
Geomatic engineering
Information and computing sciences
Machine learning
InCR CNN
Earthquake
Building damage detection
Deep feature engineering
INCA