This is the open-source repository for all things Project Sidewalk. Our mission is to develop advanced techniques to map and assess the world's sidewalks using remote crowdsourcing, artificial intelligence, and online satellite & streetscape imagery.
Some links to help you get started:
This serves as an API implementation of the Project Sidewalk AI models for tagging and validating labels.
RampNet is a two-stage pipeline that addresses the scarcity of curb ramp detection datasets by using government location data to automatically generate over 210,000 annotated Google Street View panoramas. This new dataset is then used to train a state-of-the-art curb ramp detection model that significantly outperforms previous efforts.
Collection of tools for fetching and processing Street View imagery, adapted from code by @kotarohara
Training code for classification and prediction of Project Sidewalk tags and severity levels.
Loading…
