This dataset contains 124,885,597 computer generated building footprints in all 50 US States in GeoJSON format.
Method description
We developed a method that approximates the prediction pixels into polygons making decisions based on the whole prediction feature space. This is very different from standard approaches, e.g. Douglas-Pecker algorithm, which is greedy in nature. The method tries to impose some of a priory building properties, which are, at the moment, manually defined and automatically tuned. Some of these a priory properties are:
The building edge must be of at least some length, both relative and absolute, e.g. 3 meters
Consecutive edge angles are likely to be 90 degrees
Consecutive angles cannot be very sharp, smaller by some auto-tuned threshold, e.g. 30 degrees
Building angles likely have very few dominant angles, meaning all building edges are forming angle of (dominant angle ± nπ/2)
Login to comment.
Customer reviews