RT Conference Proceedings
T1 Vehicle overtaking hazard detection over onboard cameras using deep convolutional networks
A1 García-González, Jorge
A1 García Aguilar, Iván
A1 Medina, Daniel
A1 Luque-Baena, Rafael Marcos
A1 López-Rubio, Ezequiel
A1 Domínguez-Merino, Enrique
K1 Seguridad vial -- sistemas de visión artificial
AB The development of artificial vision systems to support driving has beenof great interest in recent years, especially after new learning models based on deeplearning. In this work, a framework is proposed for detecting road speed anomalies,taking as reference the driving vehicle. The objective is to warn the driver in realtimethat a vehicle is overtaking dangerously to prevent a possible accident. Thus,taking the information captured by the rear camera integrated into the vehicle, thesystem will automatically determine if the overtaking that other vehicles make isconsidered abnormal or dangerous or is considered normal. Deep learning-basedobject detection techniques will be used to detect the vehicles in the road image.Each detected vehicle will be tracked over time, and its trajectory will be analyzed todetermine the approach speed. Finally, statistical regression techniques will estimatethe degree of anomaly or hazard of said overtaking as a preventive measure. Thisproposal has been tested with a significant set of actual road sequences in differentlighting conditions with very satisfactory results.
YR 2022
FD 2022
LK https://hdl.handle.net/10630/25176
UL https://hdl.handle.net/10630/25176
LA spa
NO Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026