A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework
More bridges today require maintenance with age, owing to increasing structural loads from traffic and natural disasters. Routine inspection for damages, including in the aftermath of special events, is conducted by experts. To address the limitations of human inspection, deep-learning-based analysi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/24/12868 |
_version_ | 1797461563948400640 |
---|---|
author | Sung-Sam Hong Cheol-Hoon Hwang Su-Wan Chung Byung-Kon Kim |
author_facet | Sung-Sam Hong Cheol-Hoon Hwang Su-Wan Chung Byung-Kon Kim |
author_sort | Sung-Sam Hong |
collection | DOAJ |
description | More bridges today require maintenance with age, owing to increasing structural loads from traffic and natural disasters. Routine inspection for damages, including in the aftermath of special events, is conducted by experts. To address the limitations of human inspection, deep-learning-based analysis of bridge damage is being actively conducted. However, such models exhibit deteriorated performance in classifying multiple classes. Most existing algorithms do not use in situ images. Hence, the results of the model training do not accurately reflect the actual damage. This study utilizes an extant method and proposes a new model of combination training by bridge member. By integrating the two approaches, we propose a bridge damaged-object-detection deep-combination framework (BDODC-F). To ensure variety in the type of damaged objects and enhanced model performance, a deep-learning-based super-resolution module is employed. For performance improvement and optimization, a deep-learning combination model based on individual training by bridge member is proposed. The BDODC-F improved the mean average precision by 191.6% and 112.21% in the combination model. We expect the framework to aid engineers in the automated detection and identification of bridge damage. |
first_indexed | 2024-03-09T17:22:10Z |
format | Article |
id | doaj.art-7d598290ef114d93a917b66920f73585 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T17:22:10Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-7d598290ef114d93a917b66920f735852023-11-24T13:06:11ZengMDPI AGApplied Sciences2076-34172022-12-0112241286810.3390/app122412868A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination FrameworkSung-Sam Hong0Cheol-Hoon Hwang1Su-Wan Chung2Byung-Kon Kim3Department of Multimedia Contents, Jangan University, Hwaseong-si 13557, Gyeonggi-do, Republic of KoreaDepartment of Research & Development, Rabahgroow Corporation, Yongin-si 16942, Gyeonggi-do, Republic of KoreaDepartment of Future and Smart Construction Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang 10223, Gyeonggi-do, Republic of KoreaDepartment of Future and Smart Construction Research, Korea Institute of Civil Engineering and Building Technology (KICT), Goyang 10223, Gyeonggi-do, Republic of KoreaMore bridges today require maintenance with age, owing to increasing structural loads from traffic and natural disasters. Routine inspection for damages, including in the aftermath of special events, is conducted by experts. To address the limitations of human inspection, deep-learning-based analysis of bridge damage is being actively conducted. However, such models exhibit deteriorated performance in classifying multiple classes. Most existing algorithms do not use in situ images. Hence, the results of the model training do not accurately reflect the actual damage. This study utilizes an extant method and proposes a new model of combination training by bridge member. By integrating the two approaches, we propose a bridge damaged-object-detection deep-combination framework (BDODC-F). To ensure variety in the type of damaged objects and enhanced model performance, a deep-learning-based super-resolution module is employed. For performance improvement and optimization, a deep-learning combination model based on individual training by bridge member is proposed. The BDODC-F improved the mean average precision by 191.6% and 112.21% in the combination model. We expect the framework to aid engineers in the automated detection and identification of bridge damage.https://www.mdpi.com/2076-3417/12/24/12868deep learningaging bridge managementimage analysisimage processingclassifier combination |
spellingShingle | Sung-Sam Hong Cheol-Hoon Hwang Su-Wan Chung Byung-Kon Kim A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework Applied Sciences deep learning aging bridge management image analysis image processing classifier combination |
title | A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework |
title_full | A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework |
title_fullStr | A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework |
title_full_unstemmed | A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework |
title_short | A Deep-Learning-Based Bridge Damaged Object Automatic Detection Model Using a Bridge Member Model Combination Framework |
title_sort | deep learning based bridge damaged object automatic detection model using a bridge member model combination framework |
topic | deep learning aging bridge management image analysis image processing classifier combination |
url | https://www.mdpi.com/2076-3417/12/24/12868 |
work_keys_str_mv | AT sungsamhong adeeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT cheolhoonhwang adeeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT suwanchung adeeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT byungkonkim adeeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT sungsamhong deeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT cheolhoonhwang deeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT suwanchung deeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework AT byungkonkim deeplearningbasedbridgedamagedobjectautomaticdetectionmodelusingabridgemembermodelcombinationframework |