Research on Multi-Dimensional and Multi-Level Environmental Parameter System for Visual Perception of Urban Tunnel Portal Sections Based on Structure–Light–Traffic (SLT) Coupling

As a transition zone between open road environments and enclosed tunnel spaces, urban tunnel entrances undergo rapid variations in spatial structure, lighting conditions, and traffic-related semantic information over short distances. These abrupt environmental changes impose considerable visual demands on drivers and may adversely affect the reliability of autonomous driving perception systems. However, existing studies have primarily investigated individual environmental factors, while lacking a systematic parameterized framework capable of characterizing multi-source environmental features and their coupled effects on visual perception. To address this limitation, this study proposes a multidimensional and multilevel environmental parameter system for urban tunnel entrances based on a Structure–Lighting–Traffic (SLT) coupling framework. First, considering the formation mechanism of visual information, environmental factors influencing perception performance in tunnel entrance zones are categorized into three dimensions: spatial structure, lighting environment, and traffic semantics, thereby establishing a unified representation framework. Subsequently, an SLT coupling model is developed, incorporating parameter gradient intensity, coupling strength, and dispersion characteristics to quantitatively characterize the spatial variation and interaction patterns of environmental parameters. Furthermore, by integrating autonomous driving perception tasks, the relationships between environmental parameter variations, image quality degradation, and perception performance are investigated. The proposed framework is validated using field measurements collected from the entrance zones of 20 urban tunnels in Chongqing, China. The results reveal pronounced spatial heterogeneity and directional asymmetry in tunnel entrance environments. The entrance transition sections exhibit the characteristics of “high variation, strong coupling, and low stability,” whereas exit transition sections demonstrate more complex multi-factor interactions due to the combined effects of structural variations, intense light intrusion, and overlapping traffic information. Compared with structural and traffic-related factors, lighting variations play a dominant role in the degradation of overall visual perception performance. The proposed SLT-based environmental parameter system establishes a unified representation framework linking human visual perception mechanisms with machine vision perception modeling, providing theoretical support for autonomous driving perception optimization, complex scene understanding, and safety risk assessment in urban tunnel environments.