We describe our automatic generative algorithm to create street addresses from satellite\nimages by learning and labeling roads, regions, and address cells. Currently, 75% of the world�s roads\nlack adequate street addressing systems. Recent geocoding initiatives tend to convert pure latitude\nand longitude information into a memorable form for unknown areas. However, settlements are\nidentified by streets, and such addressing schemes are not coherent with the road topology. Instead,\nwe propose a generative address design that maps the globe in accordance with streets. Our algorithm\nstarts with extracting roads from satellite imagery by utilizing deep learning. Then, it uniquely labels\nthe regions, roads, and structures using some graph- and proximity-based algorithms. We also\nextend our addressing scheme to (i) cover inaccessible areas following similar design principles;\n(ii) be inclusive and flexible for changes on the ground; and (iii) lead as a pioneer for a unified\nstreet-based global geodatabase. We present our results on an example of a developed city and\nmultiple undeveloped cities. We also compare productivity on the basis of current ad hoc and new\ncomplete addresses. We conclude by contrasting our generative addresses to current industrial and\nopen solutions.
Loading....