CitySurfaces

CitySurfaces is a framework that combines active learning and semantic segmentation to locate, delineate, and classify sidewalk paving materials from street-level images. Our framework adopts a recent high-performing semantic segmentation model (Tao et al., 2020), which uses hierarchical multi-scale attention combined with object-contextual representations.

The framework was presented in our paper published at the Sustainable Cities and Society journal (Arxiv link here).

For more information, check our GitHub project: https://github.com/VIDA-NYU/city-surfaces