A deep learning and full consistency approach to roadway safety scoring

Abstract

The World Health Organization (WHO) estimated that worldwide road traffic crashes account for 1.35 million annual deaths in 2018. Most studies in road safety field have focused on studying road features effect on crash frequency and injury severity. However, limited studies use automatic road features detection methods to evaluate road safety. This research applies deep learning object detection to automatically identify roads features and Full Consistency Method (FUCOM) to rank the effect of road features on safety. A deep artificial network object detector is trained to efficiently detect road objects in a front-facing camera image, then FUCOM is applied to determine safety weights for ten Key Safety Indicators (KSIs). After determining final weights, the proposed approach is applied on a case study in Greater Cairo, in which 354 km of multi-class roads are divided to 1-km sections and assigned a road safety score (RSS). The resulting RSS identifies areas that exhibit low safety scores, enabling decision makers to focus their efforts on features that can attain highest improvement. This research contributes to supporting governments and roadway asset management agencies in prioritizing their efforts (and funding) in addressing roadway safety – especially where structured historical data collection programs are largely missing.