Using Deep Learning for the Dynamic Evaluation of Road Marking Features from Laser Imaging

Maxime Tual, Valérie Muzet, Philippe Foucher, Christophe Heinkelé, Pierre Charbonnier

2024

Abstract

Road markings are essential guidance elements for both drivers and driver assistance systems: their maintenance requires regularly scheduled performance surveys. In this paper, we introduce a deep learning based method to estimate two indicators of the quality of road markings (the percentage of remaining marking and the contrast) directly from their appearance, using reflectance data acquired by a mobile laser imaging system used for inspections. To do this, we enhance the EfficientDet architecture by adding an output sub-network to predict the indicators. It is not possible to physically establish large-scale reference measurements for training and testing our model, but this can be done indirectly by semi-supervised image annotation, a strategy validated by our experiments. Our results show that it is advisable to train the model end-to-end without optimizing its detection performance. They also enlighten the very good accuracy of the indicators predicted by the model.

Paper Citation

in Harvard Style

Tual M., Muzet V., Foucher P., Heinkelé C. and Charbonnier P. (2024). Using Deep Learning for the Dynamic Evaluation of Road Marking Features from Laser Imaging. In Proceedings of the 4th International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE; ISBN 978-989-758-693-4, SciTePress, pages 23-31. DOI: 10.5220/0012595600003720

in Bibtex Style

@conference{improve24,
author={Maxime Tual and Valérie Muzet and Philippe Foucher and Christophe Heinkelé and Pierre Charbonnier},
title={Using Deep Learning for the Dynamic Evaluation of Road Marking Features from Laser Imaging},
booktitle={Proceedings of the 4th International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE},
year={2024},
pages={23-31},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012595600003720},
isbn={978-989-758-693-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 4th International Conference on Image Processing and Vision Engineering - Volume 1: IMPROVE
TI - Using Deep Learning for the Dynamic Evaluation of Road Marking Features from Laser Imaging
SN - 978-989-758-693-4
AU - Tual M.
AU - Muzet V.
AU - Foucher P.
AU - Heinkelé C.
AU - Charbonnier P.
PY - 2024
SP - 23
EP - 31
DO - 10.5220/0012595600003720
PB - SciTePress