Road Deterioration detection A Machine Learning-Based System for Automated Pavement Crack Identification and Analysis
Conference paper
Ganeshan, D., Sharif, S., Apeagyei, A. and Elmedany, W. 2023. Road Deterioration detection A Machine Learning-Based System for Automated Pavement Crack Identification and Analysis. 3ICT 2023: International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies. University of Bahrain, Bahrain 20 - 21 Nov 2023 IEEE. https://doi.org/10.1109/3ICT60104.2023.10391802
Authors | Ganeshan, D., Sharif, S., Apeagyei, A. and Elmedany, W. |
---|---|
Type | Conference paper |
Abstract | Road surfaces may deteriorate over time because of a number of external factors such as heavy traffic, unfavourable weather, and poor design. These flaws, which may include potholes, fissures, and uneven surfaces, can pose significant safety threats to both vehicles and pedestrians. This research aims to develop and evaluate an automated system for detecting and analyzing cracks in pavements based on machine learning. The research explores the utilisation of object detection techniques to identify and categorize different types of pavement cracks. Additionally, the proposed work investigates several approaches to integrate the outcome system with existing pavement management systems to enhance road maintenance and sustainability. The research focuses on identifying reliable data sources, creating accurate and effective object detection algorithms for pavement crack detection, classifying various types of cracks, and assessing their severity and extent. The research objectives include gathering reliable datasets, developing a precise and effective object detection algorithm, classifying different types of pavement cracks, and determining the severity and extent of the cracks. The study collected pavement crack images from various sources, including publicly available databases and images captured using mobile devices. Multiple object detection models, such as YOLOv5, YOLOv8, and CenterNet were trained and tested using the collected dataset. The proposed approaches were evaluated using different performance metrics, The achieved results indicated that the YOLOv5 model outperformed CenterNet by a significant |
Year | 2023 |
Conference | 3ICT 2023: International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies |
Publisher | IEEE |
Accepted author manuscript | License File Access Level Anyone |
Publication dates | |
Online | 19 Jan 2024 |
Publication process dates | |
Accepted | 14 Sep 2023 |
Deposited | 25 Sep 2023 |
Journal citation | pp. 188-194 |
ISSN | 2770-7466 |
2770-7458 | |
Book title | Proceedings: International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT 2023) |
ISBN | 9798350307788 |
9798350307771 | |
Digital Object Identifier (DOI) | https://doi.org/10.1109/3ICT60104.2023.10391802 |
Web address (URL) of conference proceedings | https://ieeexplore.ieee.org/xpl/conhome/10391285/proceeding |
Copyright holder | © 2023, IEEE |
Copyright information | Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
https://repository.uel.ac.uk/item/8wq09
Download files
248
total views126
total downloads4
views this month1
downloads this month