RT info:eu-repo/semantics/article
T1 Road safety evaluation through automatic extraction of road horizontal alignments from Mobile LiDAR System and inductive reasoning based on a decision tree
A1 José Antonio, Martín-Jimenez
A1 Santiago, Zazo
A1 José Juan, Arranz Justel
A1 Pablo, Rodríguez-Gonzálvez
A1 Diego, González-Aguilera
A2 Ingeniería CartograficaGeodesica y Fotogrametria
K1 Cartografía
K1 Road safety
K1 Decision tree
K1 Geometric design consistency
K1 Horizontal alignment parameters
K1 Mobile LiDAR System
AB Safe roads are a necessity for any society because of the high social costs of traffic accidents. This challenge is addressed by a novel methodology that allows us to evaluate road safety from Mobile LiDAR System data, taking advantage of the road alignment due to its influence on the accident rate. Automation is obtained through an inductive reasoning process based on a decision tree that provides a potential risk assessment. To achieve this, a 3D point cloud is classified by an iterative and incremental algorithm based on a 2.5D and 3D Delaunay triangulation, which apply different algorithms sequentially. Next, an automatic extraction process of road horizontal alignment parameters is developed to obtain geometric consistency indexes, based on a joint triple stability criterion. Likewise, this work aims to provide a powerful and effective preventive and/or predictive tool for road safety inspections. The proposed methodology was implemented on three stretches of Spanish roads, each with different traffic conditions that represent the most common road types. The developed methodology was successfully validated through as-built road projects, which were considered as “ground truth.”
PB Elsevier
YR 2019
FD 2019-07-04
LK http://hdl.handle.net/10612/10998
UL http://hdl.handle.net/10612/10998
NO ISPRS Journal of Photogrammetry & Remote Sensing
NO 13 p.
DS BULERIA. Repositorio Institucional de la Universidad de León
RD 25-abr-2024