Sidewalk Measurements from Satellite Images: Preliminary Findings
This work addresses urban planning and accessibility issues, particularly for wheelchair users, by providing a scalable method to analyze sidewalks, though it is incremental as it builds on existing computer vision techniques applied to new data.
The authors tackled the problem of large-scale analysis of pedestrian infrastructure by training a computer vision model to detect sidewalks, roads, and buildings from satellite images, achieving 83% mIoU on a test set, and applied shape analysis to study sidewalk attributes like width and curvature.
Large-scale analysis of pedestrian infrastructures, particularly sidewalks, is critical to human-centric urban planning and design. Benefiting from the rich data set of planimetric features and high-resolution orthoimages provided through the New York City Open Data portal, we train a computer vision model to detect sidewalks, roads, and buildings from remote-sensing imagery and achieve 83% mIoU over held-out test set. We apply shape analysis techniques to study different attributes of the extracted sidewalks. More specifically, we do a tile-wise analysis of the width, angle, and curvature of sidewalks, which aside from their general impacts on walkability and accessibility of urban areas, are known to have significant roles in the mobility of wheelchair users. The preliminary results are promising, glimpsing the potential of the proposed approach to be adopted in different cities, enabling researchers and practitioners to have a more vivid picture of the pedestrian realm.