arXiv cs.CY· Dongdong Wang, Alina Hagen, Isabelle Gatmaitan, Hao Zhou, Yiwen Dong, Shabboo Valipoor, Vivian W. H. Wong, Lingyao Li·· 12 小时前AI 评分31
视觉语言模型能否感知传感器所感？一种面向街景轮椅无障碍评估的可扩展专家引导设计
Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View
AI 导读
研究提出专家引导的检索增强框架，结合 Google Street View 影像、ADA 指南与专家评分规则，评估轮椅无障碍的多维度障碍。在佛罗里达大学校园采集 407 个 GSV 地点并关联 GPS 轮椅停留行为，专家引导配置将 VLM 评分与停留时间的负相关从 r=-0.40 提升至 r=-0.54。路缘坡道、人行横道等视觉线索与更高无障碍评分相关，但对细微路面状况和临时障碍的识别仍有限。
正文 · 原文
Abstract:Assessing built-environment interaction, such as wheelchair accessibility, is challenging because real-world mobility is shaped by context-dependent and temporary barriers that are difficult to capture at scale. This paper examines whether vision-language models (VLMs) can identify potential accessibility barriers from Google Street View (GSV) imagery. We propose an expert-guided retrieval-augmented framework that combines GSV imagery, ADA-informed guidance, and expert-derived rubrics to evaluate multiple accessibility dimensions. We collect a campus-scale dataset at the University of Florida, linking 407 unique GSV locations with GPS-derived wheelchair dwell behavior as a proxy for potential mobility friction. Results show that VLM ratings are negatively correlated with dwell time and exhibit distributional similarity, with the expert-guided configuration strengthening the correlation from $r=-0.40$ to $r=-0.54$ for the strongest model. Visual cue analysis further shows that features such as curb ramps and crosswalks are associated with higher VLM accessibility scores, while correspondence remains limited for subtle surface conditions, transient obstructions, and viewpoint-dependent barriers. Overall, our findings demonstrate the potential of expert-guided VLMs for scalable preliminary accessibility screening and prioritizing locations for further investigation.
| Comments: | Accepted to IEEE/CVF WACV 2027. 8 pages of main content, 2 pages of references |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY) |
| Cite as: | arXiv:2606.07642 [cs.CV] |
| (or arXiv:2606.07642v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.07642 arXiv-issued DOI via DataCite |
Submission history
From: Dongdong Wang [view email]
[v1]
Mon, 1 Jun 2026 18:46:43 UTC (5,303 KB)
[v2]
Thu, 5 Nov 2026 03:55:06 UTC (4,397 KB)
来源：arXiv cs.CY · arxiv.org