Detecting Sidewalk Accessibility Problems Using Streetscape Imagery

Recent work has applied machine learning methods to automatically find and/or assess pedestrian infrastructure in online map imagery (e.g., satellite photos, streetscape panoramas). While promising, these methods have been limited by two interrelated issues: small training sets and the choice of machine learning model.

I have this challenge

the problem

Sidewalks should benefit all of us. They provide a safe, environmentally-friendly conduit for moving about a city. For people with disabilities, sidewalks can have a significant impact on independence , quality of life, and overall physical activity. While mapping tools like Google and Apple Maps have begun offering pedestrian-focused features, they do not incorporate sidewalk routes or information on sidewalk accessibility, which limits their utility and disproportionately affects people with disabilities

Traditionally, sidewalk audits—which gather data on the presence and quality of sidewalks—are performed via in-person inspections by city transit departments or community volunteers. However, these audits are expensive, labor intensive, and infrequent.

attributions

https://kurti.sh/pubs/sidewalk_cv_assets_final_fixed_accessible.pdf

Emily Nelson

https://www.linkedin.com/in/emily-nelson-bbaba7183/

Input Needed From Contributing Editors

(click on any tag to contribute)