Advancing road maintenance with EfficientDet-based pothole monitoring

Effective road maintenance is crucial for ensuring safe and efficient transportation but is often compromised by the widespread occurrence of potholes. This study introduces a novel approach using an EfficientDet-based model for sophisticated pothole monitoring. Potholes pose a significant...

Full description

Saved in:
Bibliographic Details
Main Authors: Jenefa Archpaul, Taurshia Antony, Kuriakose Bessy Mani, Kumar Edward Naveen Vijaya, Lincy Archpaul
Format: Article
Language:English
Published: Faculty of Technical Sciences in Cacak 2025-01-01
Series:Serbian Journal of Electrical Engineering
Subjects:
Online Access:https://doiserbia.nb.rs/img/doi/1451-4869/2025/1451-48692501057J.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850174789421891584
author Jenefa Archpaul
Taurshia Antony
Kuriakose Bessy Mani
Kumar Edward Naveen Vijaya
Lincy Archpaul
author_facet Jenefa Archpaul
Taurshia Antony
Kuriakose Bessy Mani
Kumar Edward Naveen Vijaya
Lincy Archpaul
author_sort Jenefa Archpaul
collection DOAJ
description Effective road maintenance is crucial for ensuring safe and efficient transportation but is often compromised by the widespread occurrence of potholes. This study introduces a novel approach using an EfficientDet-based model for sophisticated pothole monitoring. Potholes pose a significant hazard that requires proactive detection and timely resolution. Traditional detection methods frequently fall short in terms of accuracy and real-time capability. Addressing these limitations, our research leverages the EfficientDet architecture, known for its optimal balance of accuracy and computational efficiency, to enhance the detection and monitoring of potholes. We utilized a carefully curated dataset from Kaggle, which includes 1,500 training images, 1,000 validation images, and 500 test images, encompassing a variety of real-world pothole scenarios. This diversity enables the model to generalize effectively across different conditions. Our experimental evaluations demonstrate that the EfficientDet-based model achieves an impressive average precision of 0.90 and a robust recall of 0.92, highlighting its capacity for accurate and swift pothole detection-an essential component for improving road maintenance. Moreover, we provide a comparative analysis with five contemporary pothole detection algorithms: YOLOv5, RetinaNet, CenterNet, SSD, and Faster R-CNN, among which EfficientDet consistently shows superior performance in terms of precision, recall, F1-Score, and average precision. These findings highlight the significant advancements in road safety, infrastructure management, and resource optimization. By adopting sophisticated deep learning techniques like EfficientDet, we promote a transformative improvement in road maintenance practices, paving the way for more resilient, safe, and disruptionminimized transportation networks.
format Article
id doaj-art-ddf278cbe36d406c88a3d47f6fe4d440
institution OA Journals
issn 1451-4869
2217-7183
language English
publishDate 2025-01-01
publisher Faculty of Technical Sciences in Cacak
record_format Article
series Serbian Journal of Electrical Engineering
spelling doaj-art-ddf278cbe36d406c88a3d47f6fe4d4402025-08-20T02:19:34ZengFaculty of Technical Sciences in CacakSerbian Journal of Electrical Engineering1451-48692217-71832025-01-01221577410.2298/SJEE2501057J1451-48692501057JAdvancing road maintenance with EfficientDet-based pothole monitoringJenefa Archpaul0https://orcid.org/0000-0002-6697-1788Taurshia Antony1https://orcid.org/0000-0001-9129-1859Kuriakose Bessy Mani2https://orcid.org/0009-0008-7952-7927Kumar Edward Naveen Vijaya3https://orcid.org/0009-0003-5845-2173Lincy Archpaul4https://orcid.org/0000-0002-4104-6529Karunya Institute of Technology and Sciences, School of Computer Science and Technology, Coimbatore, IndiaKarunya Institute of Technology and Sciences, School of Computer Science and Technology, Coimbatore, IndiaComputer Science and Engineering, Malla Reddy Engineering College for Women, IndiaComputer Science and Engineering, Sri Shakthi Institute of Engineering and Technology, Coimbatore, IndiaDepartment of Computer Science and Engineering, National Engineering College, Kovilpatti, Tamil Nadu, IndiaEffective road maintenance is crucial for ensuring safe and efficient transportation but is often compromised by the widespread occurrence of potholes. This study introduces a novel approach using an EfficientDet-based model for sophisticated pothole monitoring. Potholes pose a significant hazard that requires proactive detection and timely resolution. Traditional detection methods frequently fall short in terms of accuracy and real-time capability. Addressing these limitations, our research leverages the EfficientDet architecture, known for its optimal balance of accuracy and computational efficiency, to enhance the detection and monitoring of potholes. We utilized a carefully curated dataset from Kaggle, which includes 1,500 training images, 1,000 validation images, and 500 test images, encompassing a variety of real-world pothole scenarios. This diversity enables the model to generalize effectively across different conditions. Our experimental evaluations demonstrate that the EfficientDet-based model achieves an impressive average precision of 0.90 and a robust recall of 0.92, highlighting its capacity for accurate and swift pothole detection-an essential component for improving road maintenance. Moreover, we provide a comparative analysis with five contemporary pothole detection algorithms: YOLOv5, RetinaNet, CenterNet, SSD, and Faster R-CNN, among which EfficientDet consistently shows superior performance in terms of precision, recall, F1-Score, and average precision. These findings highlight the significant advancements in road safety, infrastructure management, and resource optimization. By adopting sophisticated deep learning techniques like EfficientDet, we promote a transformative improvement in road maintenance practices, paving the way for more resilient, safe, and disruptionminimized transportation networks.https://doiserbia.nb.rs/img/doi/1451-4869/2025/1451-48692501057J.pdfroad maintenancepothole detectionefficientdettransportation infrastructurereal-time monitoring
spellingShingle Jenefa Archpaul
Taurshia Antony
Kuriakose Bessy Mani
Kumar Edward Naveen Vijaya
Lincy Archpaul
Advancing road maintenance with EfficientDet-based pothole monitoring
Serbian Journal of Electrical Engineering
road maintenance
pothole detection
efficientdet
transportation infrastructure
real-time monitoring
title Advancing road maintenance with EfficientDet-based pothole monitoring
title_full Advancing road maintenance with EfficientDet-based pothole monitoring
title_fullStr Advancing road maintenance with EfficientDet-based pothole monitoring
title_full_unstemmed Advancing road maintenance with EfficientDet-based pothole monitoring
title_short Advancing road maintenance with EfficientDet-based pothole monitoring
title_sort advancing road maintenance with efficientdet based pothole monitoring
topic road maintenance
pothole detection
efficientdet
transportation infrastructure
real-time monitoring
url https://doiserbia.nb.rs/img/doi/1451-4869/2025/1451-48692501057J.pdf
work_keys_str_mv AT jenefaarchpaul advancingroadmaintenancewithefficientdetbasedpotholemonitoring
AT taurshiaantony advancingroadmaintenancewithefficientdetbasedpotholemonitoring
AT kuriakosebessymani advancingroadmaintenancewithefficientdetbasedpotholemonitoring
AT kumaredwardnaveenvijaya advancingroadmaintenancewithefficientdetbasedpotholemonitoring
AT lincyarchpaul advancingroadmaintenancewithefficientdetbasedpotholemonitoring