Dynamic Visibility Recognition and Driving Risk Assessment Under Rain–Fog Conditions Using Monocular Surveillance Imagery

This study addresses the limitations of conventional highway visibility monitoring under rain–fog conditions, where fixed stations and visibility sensors provide limited spatial coverage and unstable accuracy. Considering that drivers’ visual fields are jointly affected by global fog and local spray-induced mist, a dynamic visibility recognition and risk assessment framework is proposed using roadside monocular CCTV (Closed-Circuit Television) imagery. The method integrates the Koschmieder scattering model with the dark channel prior to estimate atmospheric transmittance and derives visibility through lane-line calibration. A Monte Carlo-based coupling model simulates local visibility degradation caused by tire spray, while a safety potential field defines the low-visibility risk field force (LVRFF) combining dynamic visibility, relative speed, and collision distance. Results show that this approach achieves over 86% accuracy under heavy rain, effectively captures real-time visibility variations, and that LVRFF exhibits strong sensitivity to visibility degradation, outperforming traditional safety indicators in identifying high-risk zones. By enabling scalable, infrastructure-based visibility monitoring without additional sensing devices, the proposed framework reduces deployment cost and energy consumption while enhancing the long-term operational resilience of highway systems under adverse weather. From a sustainability perspective, the method supports safer, more reliable, and resource-efficient traffic management, contributing to the development of intelligent and sustainable transportation infrastructure.