VLMs assessed for wheelchair accessibility using Street View data

Researchers have developed a new framework to assess wheelchair accessibility using vision-language models (VLMs) and Google Street View imagery. This expert-guided approach combines visual data with accessibility guidelines and expert rubrics to evaluate mobility friction. A dataset collected at the University of Florida, correlating Street View locations with wheelchair dwell time, showed that VLM assessments partially align with behavioral indicators of accessibility challenges. AI

IMPACT This research explores the potential of VLMs for scalable accessibility assessment, aligning with sensor-derived mobility data.

RANK_REASON This is a research paper detailing a new methodology for accessibility assessment using existing AI models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Google Street View
• University of Florida

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →