Towards Human-AI Accessibility Mapping in India: VLM-Guided Annotations and POI-Centric Analysis in Chandigarh

2026-02-09

AI Summary

This study addresses the lack of systematic sidewalk accessibility assessments in Indian cities by conducting a crowdsourced annotation campaign in Chandigarh using the Project Sidewalk platform. It introduces, for the first time, a vision-language model (VLM) to dynamically generate localized task instructions and integrates points of interest (POIs) to analyze accessibility across three functional urban zones. The project adapts the annotation schema and examples to the Indian context and combines Google Street View imagery, metadata, and POI-centered spatial analysis. Across approximately 40 kilometers of roads and 230 POIs, the study identified 1,644 accessibility barriers. User evaluations of the AI-generated guidance yielded an average rating of 4.66, demonstrating the effectiveness and innovation of human-AI collaboration in localized accessibility assessment.

Technology Category

• Humans and AI: AI for Accessibility
• Planning, Routing, and Scheduling: Planning with Language Models
• Computer Vision: Language and Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Project Sidewalk is a web-based platform that enables crowdsourcing accessibility of sidewalks at city-scale by virtually walking through city streets using Google Street View. The tool has been used in 40 cities across the world, including the US, Mexico, Chile, and Europe. In this paper, we describe adaptation efforts to enable deployment in Chandigarh, India, including modifying annotation types, provided examples, and integrating VLM-based mission guidance, which adapts instructions based on a street scene and metadata analysis. Our evaluation with 3 annotators indicates the utility of AI-mission guidance with an average score of 4.66. Using this adapted Project Sidewalk tool, we conduct a Points of Interest (POI)-centric accessibility analysis for three sectors in Chandigarh with very different land uses, residential, commercial and institutional covering about 40 km of sidewalks. Across 40 km of roads audited in three sectors and around 230 POIs, we identified 1,644 of 2,913 locations where infrastructure improvements could enhance accessibility.

Problem

• accessibility mapping
• crowdsourcing
• Points of Interest (POI)
• urban infrastructure
• human-AI collaboration

Innovation

• VLM-guided annotation
• POI-centric accessibility analysis
• crowdsourced sidewalk mapping
• human-AI collaboration
• urban accessibility