V-RoAst：视觉道路评估。VLM能否依据iRAP标准成为道路安全评估器？
V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?
AI总结：
本文提出零样本VQA框架V-RoAst，利用视觉语言模型依据iRAP标准评估道路安全，并发布ThaiRAP开源数据集，验证了VLM在低成本自动道路风险评估中的潜力。
摘要：
道路安全评估至关重要但成本高昂，尤其是在大多数道路仍未评级的中低收入国家（LMICs）。传统方法需要专家标注和训练数据，而基于监督学习的方法难以在不同区域之间泛化。本文提出了V-RoAst，一个使用视觉语言模型（VLMs）的零样本视觉问答（VQA）框架，用于对iRAP标准定义的道路安全属性进行分类。我们引入了来自ThaiRAP的首个开源数据集，该数据集包含2,000多张来自泰国的精选街景图像，并为此任务进行了标注。我们在该数据集上评估了Gemini-1.5-flash和GPT-4o-mini，并将其性能与VGGNet和ResNet基线进行了基准比较。虽然VLMs在空间感知方面表现欠佳，但它们对未见过的类别具有良好的泛化能力，并提供灵活的基于提示的推理，无需重新训练。我们的结果表明，当与补充数据集成时，VLMs可以作为自动道路评估工具。这项工作是首次探索将VLMs用于零样本基础设施风险评估，并为自动化、低成本的道路安全制图开辟了新方向。代码和数据集：https://github.com/PongNJ/V-RoAst。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
