Project Sidewalk

An open-source web-based crowdsourcing tool developed at the University of Washington that enables volunteers to virtually audit sidewalk accessibility using Google Street View panoramas. Contributors label four types of accessibility features and problems: curb ramps, missing curb ramps, sidewalk obstructions, and surface problems. The resulting dataset — containing hundreds of thousands of geo-located accessibility labels — has been used to train machine learning models for automated sidewalk assessment and to create accessibility-aware maps. Project Sidewalk has been deployed in multiple cities including Washington D.C., Seattle, and Newberg, Oregon.