Road Damage Detection Using Yolov9-Based Imagery

Road damage is one of the leading factors contributing to traffic accidents. Rapid identification and repair of damaged roads are crucial in road infrastructure management. This study aims to develop an effective method for detecting road damage, utilizing the YOLOv9 algorithm as a key component, su...

Full description

Saved in:
Bibliographic Details
Main Authors: Febrian Akbar Azhari, Tatang Rohana, Kiki Ahmad Baihaqi, Ahmad Fauzi
Format: Article
Language:English
Published: LPPM ISB Atma Luhur 2025-05-01
Series:Jurnal Sisfokom
Subjects:
Online Access:https://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/2377
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849416871164510208
author Febrian Akbar Azhari
Tatang Rohana
Kiki Ahmad Baihaqi
Ahmad Fauzi
author_facet Febrian Akbar Azhari
Tatang Rohana
Kiki Ahmad Baihaqi
Ahmad Fauzi
author_sort Febrian Akbar Azhari
collection DOAJ
description Road damage is one of the leading factors contributing to traffic accidents. Rapid identification and repair of damaged roads are crucial in road infrastructure management. This study aims to develop an effective method for detecting road damage, utilizing the YOLOv9 algorithm as a key component, such as cracks and potholes, using the Convolutional Neural Network (CNN) approach. YOLOv9 was chosen due to its efficient architecture, which enables real-time object detection, and its proven effectiveness in various object detection tasks. An annotated dataset of road images was used during the model training and testing process. The results show that the YOLOv9 model can accurately detect road damage. The model achieved a precision of 0.85 and a recall of 0.992 for pothole detection, and a precision of 0.94 for crack detection. Evaluation using mAP50 yielded a score of 0.96, while mAP50-95 reached 0.77, indicating strong detection and classification capability. A consistent decline in loss functions during training also signifies effective learning by the model. These findings suggest that YOLOv9 has the potential to be implemented in automated road damage detection systems, which can accelerate maintenance processes and enhance road user safety.
format Article
id doaj-art-eb0e42bbb9f2479d8f8bbe2f702035b5
institution Kabale University
issn 2301-7988
2581-0588
language English
publishDate 2025-05-01
publisher LPPM ISB Atma Luhur
record_format Article
series Jurnal Sisfokom
spelling doaj-art-eb0e42bbb9f2479d8f8bbe2f702035b52025-08-20T03:33:02ZengLPPM ISB Atma LuhurJurnal Sisfokom2301-79882581-05882025-05-0114219620110.32736/sisfokom.v14i2.23772040Road Damage Detection Using Yolov9-Based ImageryFebrian Akbar Azhari0Tatang Rohana1Kiki Ahmad Baihaqi2Ahmad Fauzi3Department of Computer Science, University of Buana Perjuangan Karawang Department of Computer Science, University of Buana Perjuangan Karawang Department of Computer Science, University of Buana Perjuangan Karawang Department of Computer Science, University of Buana Perjuangan Karawang `Road damage is one of the leading factors contributing to traffic accidents. Rapid identification and repair of damaged roads are crucial in road infrastructure management. This study aims to develop an effective method for detecting road damage, utilizing the YOLOv9 algorithm as a key component, such as cracks and potholes, using the Convolutional Neural Network (CNN) approach. YOLOv9 was chosen due to its efficient architecture, which enables real-time object detection, and its proven effectiveness in various object detection tasks. An annotated dataset of road images was used during the model training and testing process. The results show that the YOLOv9 model can accurately detect road damage. The model achieved a precision of 0.85 and a recall of 0.992 for pothole detection, and a precision of 0.94 for crack detection. Evaluation using mAP50 yielded a score of 0.96, while mAP50-95 reached 0.77, indicating strong detection and classification capability. A consistent decline in loss functions during training also signifies effective learning by the model. These findings suggest that YOLOv9 has the potential to be implemented in automated road damage detection systems, which can accelerate maintenance processes and enhance road user safety.https://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/2377yolov9road damage detectioncnndeep learningmachine learning
spellingShingle Febrian Akbar Azhari
Tatang Rohana
Kiki Ahmad Baihaqi
Ahmad Fauzi
Road Damage Detection Using Yolov9-Based Imagery
Jurnal Sisfokom
yolov9
road damage detection
cnn
deep learning
machine learning
title Road Damage Detection Using Yolov9-Based Imagery
title_full Road Damage Detection Using Yolov9-Based Imagery
title_fullStr Road Damage Detection Using Yolov9-Based Imagery
title_full_unstemmed Road Damage Detection Using Yolov9-Based Imagery
title_short Road Damage Detection Using Yolov9-Based Imagery
title_sort road damage detection using yolov9 based imagery
topic yolov9
road damage detection
cnn
deep learning
machine learning
url https://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/2377
work_keys_str_mv AT febrianakbarazhari roaddamagedetectionusingyolov9basedimagery
AT tatangrohana roaddamagedetectionusingyolov9basedimagery
AT kikiahmadbaihaqi roaddamagedetectionusingyolov9basedimagery
AT ahmadfauzi roaddamagedetectionusingyolov9basedimagery