Pothole Detection under Diverse Conditions using Object Detection Models

Syed Hassan, Dympna O’Sullivan, Susan Mckeever

Abstract

One of the most important tasks in road maintenance is the detection of potholes. This process is usually done through manual visual inspection, where certified engineers assess recorded images of pavements acquired using cameras or professional road assessment vehicles. Machine learning techniques are now being applied to this problem, with models trained to automatically identify road conditions. However, approaching this real-world problem with machine learning techniques presents the classic problem of how to produce generalisable models. Images and videos may be captured in different illumination conditions, with different camera types, camera angles and resolutions. In this paper we present our approach to building a generalized learning model for pothole detection. We apply four datasets that contain a range of image and environment conditions. Using the Faster RCNN object detection model, we demonstrate the extent to which pothole detection models can generalise across various conditions. Our work is a contribution to bringing automated road maintenance techniques from the research lab into the real-world.

Download


Paper Citation


in Harvard Style

Hassan S., O’Sullivan D. and Mckeever S. (2021). Pothole Detection under Diverse Conditions using Object Detection Models. In Proceedings of the International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE, ISBN 978-989-758-511-1, pages 128-136. DOI: 10.5220/0010463701280136


in Bibtex Style

@conference{improve21,
author={Syed Hassan and Dympna O’Sullivan and Susan Mckeever},
title={Pothole Detection under Diverse Conditions using Object Detection Models},
booktitle={Proceedings of the International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,},
year={2021},
pages={128-136},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010463701280136},
isbn={978-989-758-511-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE,
TI - Pothole Detection under Diverse Conditions using Object Detection Models
SN - 978-989-758-511-1
AU - Hassan S.
AU - O’Sullivan D.
AU - Mckeever S.
PY - 2021
SP - 128
EP - 136
DO - 10.5220/0010463701280136