Driving impairment detection due to sun exposure and contrasting shadow of surface objects: an urban case study

Abstract

A change in the driver’s vision quality might result in deterioration of their perception and effectiveness. The lack of an integrated algorithm to distinguish the location of driver vision impairment motivated this study. The proposed model benefits from a combination of several sub-algorithms such as sun positioning, glare detection, and contrasting shadow illustrator derived from raw geospatial data. The methodology is implemented through a case study involving a road network in a large metropolitan area, a digital elevation model, the associated hillshade geographic data, and weather data from Montreal, Canada. The methodology and corresponding data analysis were implemented in Python. The results revealed a geospatial model to estimate the boundaries of transition points between the glare and contrasting shadows created by changes in the roadway surroundings. The results provided by the model can be used as a tool to aid decision-makers in new road construction and urban planning by creating safety countermeasure strategies and design review of road geometry.