Real-Time Driver and Traffic Data Integration for Enhanced Road Safety

Abstract

Traditional roadway safety assessment heavily relies on historical crash data, overlooking real-time factors such as driver behaviors and current traffic conditions and lacking forward-looking analysis for predicting future trends. This study introduces an enhanced innovative data fusion method based on the safe route mapping (SRM) methodology with combined use of historical crash data and real-time data, leveraging a custom-built Android app to amalgamate road and vehicle data effectively, showcasing notable advancements in real-time risk assessment. The enhanced safe route mapping (ESRM) framework monitors driver actions and road conditions meticulously. Data collected from drivers is analyzed on a central server using facial recognition algorithm to detect signs of fatigue and distractions, assessing overall driving competence. Simultaneously, roadside cameras capture live traffic data, analyzed using a specialized video analytics method to track vehicle speed and paths. The fusion of these data streams enables the introduction of a predictive model, Light gradient boosting machine (GBM), forecasting potential immediate issues for drivers. Predicted risk scores are integrated with historical crash data using a Fuzzy logic model, delineating risk levels for different road sections. The performance of ESRM model is tested using real-world data and a driving simulation, demonstrating remarkable accuracy, especially in accounting for real-time fusion of driver behavior and traffic conditions. The resultant visual risk heatmap aids authorities in identifying safer routes, proactive law enforcement deployment, and informed trip planning based on real-time risk levels. This study not only underscores the importance of real-time data in roadway safety but also paves the way for data-driven, dynamic risk assessment models, potentially reducing road accidents and fostering a safer driving environment.