Citation

De Nicolao G, Ferrara A, Giacomini L. IEEE Trans. Vehicular Tech. 2007; 56(5): 2405-2413.

Copyright

(Copyright © 2007, IEEE (Institute of Electrical and Electronics Engineers))

DOI

unavailable

PMID

unavailable

Abstract

In this paper, the authors present a novel approach for assessing the risk of vehicular collisions with pedestrians based on scenarios and pedestrian behaviors. The approach relies on a sensor system that is able to classify the pedestrians and determinant relevant data such as vehicle velocity and relative position and velocity. The collision Risk Assessment Unit, affiliated with the European Commission's PROTECTOR project, is used to filter out irrelevant detections. This then allows the man machine interface to generate a collision warning to the driver only when the collision risk associated with the specific traffic scenario is above a pre-specified threshold. Monte Carlo simulations are used to evaluate collision probabilities.