A VLM-Enhanced Framework for Comprehensive Traffic Sign Condition Assessment Integrating Daytime Visual Performance and Nighttime Retroreflectivity Evaluation

2026-07-07

AI Summary

This study addresses the limitations of conventional traffic sign assessment, which relies heavily on manual inspections and typically evaluates either daytime visibility or nighttime retroreflectivity in isolation, lacking an integrated approach. To bridge this gap, the authors propose the first unified evaluation framework that jointly quantifies daytime visual performance and nighttime retroreflective properties. Specifically, they fine-tune vision-language models—LLaVA, Qwen, and InternVL—to assess four key daytime visual factors and integrate these with LiDAR-derived retroreflectivity measurements to formulate a Sign Condition Index (SCI) for maintenance decision support. Experiments on 462 traffic signs demonstrate the framework’s effectiveness in identifying 68 signs requiring immediate replacement, with LLaVA and Qwen achieving the highest performance (bidirectional cosine similarity of 0.67–0.76), thereby validating the method’s accuracy and cost-efficiency.

Abstract

Traffic signs are crucial components of road safety, serving as visual tools under all lighting conditions. The Manual on Uniform Traffic Control Devices (MUTCD) specifies daytime visual factors such as legibility and color contrast, and nighttime retroreflectivity requirements. Traditional assessment methods rely on manual inspections, which the Federal Highway Administration (FHWA) notes are subjective, labor-intensive and pose safety concerns, while retroreflectometers are expensive and unaffordable for smaller agencies. Most existing studies focus on either daytime factors or nighttime retroreflectivity but rarely integrate both aspects comprehensively. This study develops a novel framework that systematically evaluates traffic signs through integrated daytime-nighttime assessment. The methodology employs three fine-tuned Vision Language Models (VLMs) for daytime visual performance assessment across four key factors: legibility, color, surface and shape integrity, and surrounding environment conditions. VLM predictions are converted to numerical scores through sentiment analysis and Contrastive Language-Image Pre-Training (CLIP) scoring, while nighttime performance is assessed using LiDAR-derived retroreflectivity following established calibration procedures. The framework integrates these components into a comprehensive Sign Condition Index (SCI) for maintenance guidance. Evaluation results demonstrated that LLaVA and Qwen outperformed InternVL, achieving bidirectional cosine similarity scores of 0.67-0.76 across all factors. Among 462 validated traffic signs, 68 were flagged by the proposed framework as requiring immediate replacement due to inadequate retroreflectivity performance. This research provides a cost-effective alternative to traditional manual inspections for comprehensive traffic sign condition assessment.

Problem

• traffic sign condition assessment
• daytime visual performance
• nighttime retroreflectivity
• integrated evaluation
• road safety

Innovation

• Vision Language Models
• Retroreflectivity
• Traffic Sign Condition Index
• CLIP scoring
• LiDAR-based assessment