The Influence of Visual Landscapes on Road Traffic Safety: An Assessment Using Remote Sensing and Deep Learning

• Main Authors: Liu L., Gao Z., Luo P., Duan W., Hu M., Mohd Arif Zainol M.R.R., Zawawi M.H.
• Other Authors: 57194520601
• Format: Article
• Published: Multidisciplinary Digital Publishing Institute (MDPI) 2024
• Subjects: deep learning; driving performance; remote sensing; semantic segmentation; street view image; traffic safety; visual landscape elements; Accident prevention; Automobile drivers; Deep learning; Heart; Highway planning; Motor transportation; Population statistics; Remote sensing; Semantic Segmentation; Semantics; Urban growth; Driver fatigue; Driving performance; Landscape elements; Landscape feature; Remote-sensing; Semantic segmentation; Street view image; Traffic safety; Visual landscape element; Roads and streets

Rapid global economic development, population growth, and increased motorization have resulted in significant issues in urban traffic safety. This study explores the intrinsic connections between road environments and driving safety by integrating multiple visual landscape elements. High-resolution remote sensing and street-view images were used as primary data sources to obtain the visual landscape features of an urban expressway. Deep learning semantic segmentation was employed to calculate visual landscape features, and a trend surface fitting model of road landscape features and driver fatigue was established based on experimental data from 30 drivers who completed driving tasks in random order. There were significant spatial variations in the visual landscape of the expressway from the city center to the urban periphery. Heart rate values fluctuated within a range of 0.2% with every 10% change in driving speed and landscape complexity. Specifically, as landscape complexity changed between 5.28 and 8.30, the heart rate fluctuated between 91 and 96. This suggests that a higher degree of landscape richness effectively mitigates increases in driver fatigue and exerts a positive impact on traffic safety. This study provides a reference for quantitative assessment research that combines urban road landscape features and traffic safety using multiple data sources. It may guide the implementation of traffic safety measures during road planning and construction. � 2023 by the authors.