PROJECT TITLE :

Quantitative model of the driver's reaction time during daytime fog – application to a head up display-based advanced driver assistance system

ABSTRACT:

Road accidents as a result of of fog are comparatively rare but their severity is greater and the chance of pile-up is higher. But, processing the photographs grabbed by cameras embedded in the vehicles can restore some visibility. Tarel et al. (2012) proposed to implement head up displays (HUD) to help drivers anticipate potential collisions by displaying dehazed images of the road scene. In this study, three experiments have been designed to quantify the expected gain of such a system in terms of the driver's reaction time (RT). The primary experiment compares the RT with and while not dehazing, giving quantitative evidence that such a complicated driving assistance system (ADAS) may improve road safety. Then, based mostly on a modified Piéron's law, a quantitative model is proposed, linking the RT to the target visibility (Vt), which will be computed from onboard camera pictures. 2 additional experiments are conducted, giving evidence that the proposed RT model, computed from Vt, is robust with respect to contextual cues, to distinction polarity and to population sample. The authors finally propose to use this predictive model to switch on/off the proposed HUD-primarily based ADAS.