Cover Image

Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms

This paper introduces a novel approach to pavement material crack detection, classification, and segmentation using advanced deep learning techniques, including multi-scale feature aggrega- tion and transformer-based attention mechanisms. The proposed methodology significantly enhances the model’s a...

Full description

Saved in:
Bibliographic Details
Main Authors: Ashraf, Arselan, Sophian, Ali, Bawono, Ali Aryo
Format: Article
Language:English
Published: MDPI 2024
Subjects:
T Technology (General)
Online Access:http://irep.iium.edu.my/116173/1/constrmater-04-00036.pdf
http://irep.iium.edu.my/116173/
https://www.mdpi.com/journal/constrmater
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.iium.irep.116173
record_format dspace
spelling my.iium.irep.1161732024-11-29T09:46:42Z http://irep.iium.edu.my/116173/ Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms Ashraf, Arselan Sophian, Ali Bawono, Ali Aryo T Technology (General) This paper introduces a novel approach to pavement material crack detection, classification, and segmentation using advanced deep learning techniques, including multi-scale feature aggrega- tion and transformer-based attention mechanisms. The proposed methodology significantly enhances the model’s ability to handle varying crack sizes, shapes, and complex pavement textures. Trained on a dataset of 10,000 images, the model achieved substantial performance improvements across all tasks after integrating transformer-based attention. Detection precision increased from 88.7% to 94.3%, and IoU improved from 78.8% to 93.2%. In classification, precision rose from 88.3% to 94.8%, and recall improved from 86.8% to 94.2%. For segmentation, the Dice Coefficient increased from 80.3% to 94.7%, and IoU for segmentation advanced from 74.2% to 92.3%. These results underscore the model’s robustness and accuracy in identifying pavement cracks in challenging real-world scenarios. This framework not only advances automated pavement maintenance but also provides a foundation for future research focused on optimizing real-time processing and extending the model’s applicability to more diverse pavement conditions. MDPI 2024-10-16 Article PeerReviewed application/pdf en http://irep.iium.edu.my/116173/1/constrmater-04-00036.pdf Ashraf, Arselan and Sophian, Ali and Bawono, Ali Aryo (2024) Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms. Construction Materials, 4. pp. 655-675. https://www.mdpi.com/journal/constrmater
institution Universiti Islam Antarabangsa Malaysia
building IIUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider International Islamic University Malaysia
content_source IIUM Repository (IREP)
url_provider http://irep.iium.edu.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Ashraf, Arselan
Sophian, Ali
Bawono, Ali Aryo
Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
description This paper introduces a novel approach to pavement material crack detection, classification, and segmentation using advanced deep learning techniques, including multi-scale feature aggrega- tion and transformer-based attention mechanisms. The proposed methodology significantly enhances the model’s ability to handle varying crack sizes, shapes, and complex pavement textures. Trained on a dataset of 10,000 images, the model achieved substantial performance improvements across all tasks after integrating transformer-based attention. Detection precision increased from 88.7% to 94.3%, and IoU improved from 78.8% to 93.2%. In classification, precision rose from 88.3% to 94.8%, and recall improved from 86.8% to 94.2%. For segmentation, the Dice Coefficient increased from 80.3% to 94.7%, and IoU for segmentation advanced from 74.2% to 92.3%. These results underscore the model’s robustness and accuracy in identifying pavement cracks in challenging real-world scenarios. This framework not only advances automated pavement maintenance but also provides a foundation for future research focused on optimizing real-time processing and extending the model’s applicability to more diverse pavement conditions.
format Article
author Ashraf, Arselan
Sophian, Ali
Bawono, Ali Aryo
author_facet Ashraf, Arselan
Sophian, Ali
Bawono, Ali Aryo
author_sort Ashraf, Arselan
title Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
title_short Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
title_full Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
title_fullStr Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
title_full_unstemmed Crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
title_sort crack detection, classification, and segmentation on road pavement material using multi-scale feature aggregation and transformer-based attention mechanisms
publisher MDPI
publishDate 2024
url http://irep.iium.edu.my/116173/1/constrmater-04-00036.pdf
http://irep.iium.edu.my/116173/
https://www.mdpi.com/journal/constrmater
_version_ 1817841079905419264
score 13.244413

Similar Items