Georeferencing of Road Infrastructure from Photographs using Computer Vision and Deep Learning for Road Safety Applications

Simon Graf, Raphaela Pagany, Wolfgang Dorner, Armin Weigold

2019

Abstract

Georeferenced information of road infrastructure is crucial for road safety analysis. Unfortunately, for essential structures, such as fences and crash barriers, exact location information and extent is often not available hindering any kind of spatial analysis. For a GIS-based study on wildlife-vehicle collisions (WVCs) and, therein, the impact of these structures, we developed a method to derive this data from video-based road inspections. A deep learning approach was applied to identify fences and barriers in photos and to estimate the extent and location, based on the photos’ metadata and perspective. We used GIS-based analysis and geometric functions to convert this data into georeferenced line segments. For a road network of 113 km, we were able to identify over 88% of all barrier lines. The main problems for the application of this method are infrastructure invisible from the road or hidden behind vegetation, and the small sections along the streets covered by photos not depicting the tops of higher dams or slopes.

Download


Paper Citation


in Harvard Style

Graf S., Pagany R., Dorner W. and Weigold A. (2019). Georeferencing of Road Infrastructure from Photographs using Computer Vision and Deep Learning for Road Safety Applications.In Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management - Volume 1: GISTAM, ISBN 978-989-758-371-1, pages 71-76. DOI: 10.5220/0007706800710076


in Bibtex Style

@conference{gistam19,
author={Simon Graf and Raphaela Pagany and Wolfgang Dorner and Armin Weigold},
title={Georeferencing of Road Infrastructure from Photographs using Computer Vision and Deep Learning for Road Safety Applications},
booktitle={Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management - Volume 1: GISTAM,},
year={2019},
pages={71-76},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007706800710076},
isbn={978-989-758-371-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management - Volume 1: GISTAM,
TI - Georeferencing of Road Infrastructure from Photographs using Computer Vision and Deep Learning for Road Safety Applications
SN - 978-989-758-371-1
AU - Graf S.
AU - Pagany R.
AU - Dorner W.
AU - Weigold A.
PY - 2019
SP - 71
EP - 76
DO - 10.5220/0007706800710076