Redirigiendo al acceso original de articulo en 23 segundos...
ARTÍCULO
TITULO

A New Road Safety Indicator Based on Vehicle Trajectory Analysis

Peggy Subirats    
Yann Goyat    
Bernard Jacob    
Eric Violette    

Resumen

In 2014, in France, accidents on rural roads accounted for roughly 63% of road mortality (ONISR, 2014). Yet, the locations of accidents are increasingly spread, and it is becoming difficult for road managers to set priorities for interventions on their road network. They can no longer base their strategy on accident analysis. Road managers need to quickly measure the effectiveness of a modified facility, improvement of facilities or modification of the environment. On this type of site accident analysis requires a period of 3 to 5 years to determine the effectiveness of a change. This period of time does not meet the requirements of road managers or road users. To provide a high safety level, managers are implementing innovative developments: wall effect chicane at crossroads, dynamic warning signs, rural roundabouts, etc. Managers want to quickly assess these innovations. In addition, they have less and less money, so it is necessary to give them tools to help prioritize their intervention. It is also preferable for road managers to take preventive action rather than having to wait for accidents or serious injuries to occur, in order to carry out diagnosis and propose countermeasures. In this article, we propose a new safety indicator based on trajectory analysis. By trajectory, we mean a time-function that describes vehicle movement including not only its path on the road but also speeds and accelerations in both horizontal directions (longitudinal and transverse). These trajectories describe vehicle/infrastructure/driver interactions and reveal inadequacies that can lead to accidents. These trajectories are obtained using two roadside observation systems that analyse vehicle trajectories on two specific locations: curves and intersections on rural roads. The first tool is a local trajectory measurement system. It records trajectories of all vehicles passing through a specific zone. The goal is to observe abnormal paths that reveal dysfunctions in the vehicle/Infrastructure/driver system. The main applications-related contribution of this work focuses on developing a comprehensive solution for accurately estimating vehicle trajectories based on a combination of video images and range finder (telemeter) measurements. The purpose of the second tool is to improve understanding of dysfunctions at a crossroads and to evaluate the effectiveness of facilities. A precise study of patterns encountered on accident-prone intersections on rural roads showed that some situations are much more dangerous and frequent than others. In particular, most accidents at intersections are caused by vehicles crossing main roads. The second system presented in this paper detects and records conflicts between users on the secondary road who are crossing the main road, and users driving straight ahead on the main road. This kind of conflict represents the main type of accidents called crossing at grade accidents. The proposed risk indicator is equal to the number of conflicts (near-misses), weighted by the severity of the conflicts recorded in a given period. We chose to take the number of conflicts per hour. The purpose of these tools is to understand anomalies in the vehicle/infrastructure/driver system, and to evaluate the effectiveness of countermeasures on safety. Associated with risk indicators they make it possible to objectively assess driver behaviours with respect to the road infrastructure.

 Artículos similares

       
 
Ramez M. Elmasry, Mohamed A. Abd El Ghany, Mohammed A.-M. Salem and Omar M. Fahmy    
Human behavior is regarded as one of the most complex notions present nowadays, due to the large magnitude of possibilities. These behaviors and actions can be distinguished as normal and abnormal. However, abnormal behavior is a vast spectrum, so in thi... ver más
Revista: AI

 
Andrea Grilli and Alex Balzi    
Local Road Administrations (LRA) manage wide and fragmented road networks with constrained financial and human resources. Though LRA manage the most road networks and the relative development and maintenance have a huge impact on environment and society,... ver más
Revista: Infrastructures

 
Pedro Nogueira, Marcelo Silva, Paulo Infante, Vitor Nogueira, Paulo Manuel, Anabela Afonso, Gonçalo Jacinto, Leonor Rego, Paulo Quaresma, José Saias, Daniel Santos and Patricia Gois    
Road traffic accidents are a major concern for modern society with a high toll on human life and involve hard to account economic consequences. New knowledge can be obtained from combining GIS tools with machine learning and artificial intelligence, deve... ver más

 
Bi Yu Chen, Huihuang Huang, Hui-Ping Chen, Wenxuan Liu, Xuan-Yan Chen and Tao Jia    
The order k Voronoi diagram (OkVD) is an effective geometric construction to partition the geographical space into a set of Voronoi regions such that all locations within a Voronoi region share the same k nearest points of interest (POIs). Despite the br... ver más

 
Son Vu Hong Pham and Khoi Van Tien Nguyen    
Artificial intelligence models are currently being proposed for application in improving performance in addressing contemporary management and production issues. With the goal of automating the detection of road surface defects in transportation infrastr... ver más
Revista: Applied Sciences