Characterizing the Cyclists’ Path-Overtaking Maneuver Detection and Vehicles’ Speed Estimation

Content Provider	Semantic Scholar
Author	Oliveira, Filipa Marqués, Manuel María Medrano
Copyright Year	2018
Abstract	The traffic pollution is a scourge of urban areas and several transportation policies have been adopted to increase the use of sustainable transportation, such as bicycles. To develop this desirable trend and design new infrastructures, policy makers require tools for cyclists’ risk assessment. In this paper, a video-based method to estimate overtaking maneuvers and vehicles’ speed is proposed. It was possible to geo-reference these stressful events for riders, providing a framework for path characterization concerning roads’ suitability and safety for cyclists. The proposed method is based on license plate recognition and tracking of approaching vehicles near cyclists surroundings. A new data set with realistic bicycle scenarios in urban roads, gathered with an action camera located at bicycle’s handlebar together with smartphone’s GPS data, is made available and used as case of study. Allowing to compare distinct streets and urban areas based on the speed of detected overtaking maneuvers. The results achieved are very promising concerning path’s characterization for cyclists.
File Format	PDF HTM / HTML
Alternate Webpage(s)	https://fenix.tecnico.ulisboa.pt/downloadFile/1126295043836225/Resumo_alargado_final.pdf
Language	English
Access Restriction	Open
Content Type	Text
Resource Type	Article