V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?

TL;DR

This paper explores using Vision-Language Models for zero-shot road safety assessment, introducing a new dataset and benchmarking their performance against traditional methods for low-cost infrastructure risk analysis.

Contribution

It presents the first open-source dataset from ThaiRAP and evaluates VLMs as flexible, zero-shot tools for road safety classification without retraining.

Findings

VLMs generalise well to unseen safety classes

They outperform traditional CNN baselines in zero-shot settings

Code and dataset are publicly available for further research

Abstract

Road safety assessments are critical yet costly, especially in Low- and Middle-Income Countries (LMICs), where most roads remain unrated. Traditional methods require expert annotation and training data, while supervised learning-based approaches struggle to generalise across regions. In this paper, we introduce \textit{V-RoAst}, a zero-shot Visual Question Answering (VQA) framework using Vision-Language Models (VLMs) to classify road safety attributes defined by the iRAP standard. We introduce the first open-source dataset from ThaiRAP, consisting of over 2,000 curated street-level images from Thailand annotated for this task. We evaluate Gemini-1.5-flash and GPT-4o-mini on this dataset and benchmark their performance against VGGNet and ResNet baselines. While VLMs underperform on spatial awareness, they generalise well to unseen classes and offer flexible prompt-based reasoning without retraining. Our results show that VLMs can serve as automatic road assessment tools when integrated with complementary data. This work is the first to explore VLMs for zero-shot infrastructure risk assessment and opens new directions for automatic, low-cost road safety mapping. Code and dataset: https://github.com/PongNJ/V-RoAst.