Application of Deep Learning Techniques in Negative Road Anomalies Detection

Jihad Dib, Konstantinos Sirlantzis, Gareth Howells

2022

Abstract

Negative Road Anomalies (Potholes, cracks, and other road anomalies) have long posed a risk for drivers driving on the road. In this paper, we apply deep learning techniques to implement a YOLO-based (You Only Look Once) network in order to detect and identify potholes in real-time providing a fast and accurate detection and sufficient time for proper safe navigation and avoidance of potholes. This system can be used in conjunction with any existing system and can be mounted to moving platforms such as autonomous vehicles. Our results show that the system is able to reach real-time processing (29.34 frames per second) with a high level of accuracy (mAP of 82.05%) and detection accuracy of 89.75% when mounted onto an Electric-Powered Wheelchair (EPW).

Paper Citation

in Harvard Style

Dib J., Sirlantzis K. and Howells G. (2022). Application of Deep Learning Techniques in Negative Road Anomalies Detection. In Proceedings of the 14th International Joint Conference on Computational Intelligence - Volume 1: ROBOVIS; ISBN 978-989-758-611-8, SciTePress, pages 475-482. DOI: 10.5220/0011336000003332

in Bibtex Style

@conference{robovis22,
author={Jihad Dib and Konstantinos Sirlantzis and Gareth Howells},
title={Application of Deep Learning Techniques in Negative Road Anomalies Detection},
booktitle={Proceedings of the 14th International Joint Conference on Computational Intelligence - Volume 1: ROBOVIS},
year={2022},
pages={475-482},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011336000003332},
isbn={978-989-758-611-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computational Intelligence - Volume 1: ROBOVIS
TI - Application of Deep Learning Techniques in Negative Road Anomalies Detection
SN - 978-989-758-611-8
AU - Dib J.
AU - Sirlantzis K.
AU - Howells G.
PY - 2022
SP - 475
EP - 482
DO - 10.5220/0011336000003332
PB - SciTePress