Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms

Economic and social prosperity heavily relies on well-maintained highways. However, road maintenance faces challenges due to limited funding and resources, with potholes posing significant safety risks. This work introduces a pothole detector designed to detect and estimate pothole areas for timely...

Full description

Saved in:
Bibliographic Details
Main Authors: Rufus Rubin, Chinnu Jacob, Sumod Sundar, Gabriel Stoian, Daniela Danciulescu, Jude Hemanth
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Advances in Civil Engineering
Online Access:http://dx.doi.org/10.1155/adce/7911336
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849765032878931968
author Rufus Rubin
Chinnu Jacob
Sumod Sundar
Gabriel Stoian
Daniela Danciulescu
Jude Hemanth
author_facet Rufus Rubin
Chinnu Jacob
Sumod Sundar
Gabriel Stoian
Daniela Danciulescu
Jude Hemanth
author_sort Rufus Rubin
collection DOAJ
description Economic and social prosperity heavily relies on well-maintained highways. However, road maintenance faces challenges due to limited funding and resources, with potholes posing significant safety risks. This work introduces a pothole detector designed to detect and estimate pothole areas for timely maintenance. It enhances detection by modifying the YOLO algorithm, using the Xception backbone, and integrating attention mechanisms to improve the prediction of small or clustered objects. Xception’s depthwise separable convolutions enhance feature extraction, outperforming the standard YOLO algorithm in detecting small, irregular potholes and preventing overfitting. The improved YOLO model, along with spatial and channel attention mechanisms, focuses on relevant regions and refines important features specific to pothole areas. Accurate area estimation is achieved through computer vision and traditional segmentation processes. A custom dataset, including the MakeML pothole dataset, a Kaggle dataset, and real-time footage of Kerala roadways, is used for training and validation. Performance evaluation with mean average precision (mAP) and average precision (AP) metrics shows the pothole detector’s superiority, effectively identifying potholes under various conditions and ensuring safe road infrastructure.
format Article
id doaj-art-ad9a75b59ffa41579b9d1f7d4ba9cb54
institution DOAJ
issn 1687-8094
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Advances in Civil Engineering
spelling doaj-art-ad9a75b59ffa41579b9d1f7d4ba9cb542025-08-20T03:04:58ZengWileyAdvances in Civil Engineering1687-80942025-01-01202510.1155/adce/7911336Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention MechanismsRufus Rubin0Chinnu Jacob1Sumod Sundar2Gabriel Stoian3Daniela Danciulescu4Jude Hemanth5Centre for Artificial IntelligenceCentre for Artificial IntelligenceCentre for Artificial IntelligenceDepartment of Computer ScienceDepartment of Computer ScienceDepartment of ECEEconomic and social prosperity heavily relies on well-maintained highways. However, road maintenance faces challenges due to limited funding and resources, with potholes posing significant safety risks. This work introduces a pothole detector designed to detect and estimate pothole areas for timely maintenance. It enhances detection by modifying the YOLO algorithm, using the Xception backbone, and integrating attention mechanisms to improve the prediction of small or clustered objects. Xception’s depthwise separable convolutions enhance feature extraction, outperforming the standard YOLO algorithm in detecting small, irregular potholes and preventing overfitting. The improved YOLO model, along with spatial and channel attention mechanisms, focuses on relevant regions and refines important features specific to pothole areas. Accurate area estimation is achieved through computer vision and traditional segmentation processes. A custom dataset, including the MakeML pothole dataset, a Kaggle dataset, and real-time footage of Kerala roadways, is used for training and validation. Performance evaluation with mean average precision (mAP) and average precision (AP) metrics shows the pothole detector’s superiority, effectively identifying potholes under various conditions and ensuring safe road infrastructure.http://dx.doi.org/10.1155/adce/7911336
spellingShingle Rufus Rubin
Chinnu Jacob
Sumod Sundar
Gabriel Stoian
Daniela Danciulescu
Jude Hemanth
Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
Advances in Civil Engineering
title Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
title_full Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
title_fullStr Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
title_full_unstemmed Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
title_short Pothole Detection and Assessment on Highways Using Enhanced YOLO Algorithm With Attention Mechanisms
title_sort pothole detection and assessment on highways using enhanced yolo algorithm with attention mechanisms
url http://dx.doi.org/10.1155/adce/7911336
work_keys_str_mv AT rufusrubin potholedetectionandassessmentonhighwaysusingenhancedyoloalgorithmwithattentionmechanisms
AT chinnujacob potholedetectionandassessmentonhighwaysusingenhancedyoloalgorithmwithattentionmechanisms
AT sumodsundar potholedetectionandassessmentonhighwaysusingenhancedyoloalgorithmwithattentionmechanisms
AT gabrielstoian potholedetectionandassessmentonhighwaysusingenhancedyoloalgorithmwithattentionmechanisms
AT danieladanciulescu potholedetectionandassessmentonhighwaysusingenhancedyoloalgorithmwithattentionmechanisms
AT judehemanth potholedetectionandassessmentonhighwaysusingenhancedyoloalgorithmwithattentionmechanisms