Visual Recognition Distance Prediction and Energy-Efficient Brightness Optimization Strategies for Active Luminous Guide Signs

In response to increasing urbanization and vehicle ownership, road traffic safety has become a critical area of study, especially under conditions of poor visibility at night or in adverse weather. Traditional retroreflective traffic signs often fail to provide sufficient visibility, increasing the risk of accidents. This research focuses on active luminous guide signs, a novel traffic management technology that has seen widespread adoption across various regions. Our paper explores the visual recognition distance of these signs by analyzing aspects of signs brightness level, vehicle speed, and ambient light conditions. Real vehicle experiments were conducted to study how those factors affect the visibility distance. The research utilizes genetic algorithm–backpropagation (GA-BP) neural network models to simulate visibility and employs a multi-objective genetic algorithm to optimize both visibility distance and energy consumption of the signs based on non-dominated sorting genetic algorithm-II (NSGA-II) and technique for order preference by similarity to ideal solution (TOPSIS). By delineating signs optimal brightness parameters across different lighting conditions and speeds, this study offers strategic insights into the brightness management of active luminous guide signs, contributing significantly to traffic safety and infrastructure digital transformation.