Abstract
Abstract Drivers face significant visibility challenges throughout the day and night due to varying environmental and lighting conditions. During the day, heavy rain and dense fog can severely reduce visibility, making it difficult to identify road markings and navigate safely. At night, the absence of natural light exacerbates visibility issues, and the intense glare from high-beam headlights further impairs focus of the driver which affects his reaction times. These challenges significantly increase the risk of accidents. To address these issues, modern vehicles are equipped with advanced systems such as front-mounted cameras and displays to improve road visibility. However, maintaining display clarity under adverse conditions remains a challenge for them. This study proposes a novel method for classifying roadway scenarios using Vision Transformer (ViT) features combined with decision-tree-based classifiers and applying tailored image enhancement algorithms for each scenario. The method effectively distinguishes between six road scenarios, including adverse weather and low-light conditions. Using Random Forest as the classification model, the proposed approach achieved a maximum accuracy of 96.60%, outperforming state-of-the-art methods. By accurately classifying scenarios and applying appropriate enhancement techniques, this approach improves road visibility and enhances driver safety.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call