Generative Street Addresses from Satellite Imagery

We describe our automatic generative algorithm to create street addresses from satellite images by learning and labeling roads, regions, and address cells. Currently, 75% of the world’s roads lack adequate street addressing systems. Recent geocoding initiatives tend to convert pure latitude and long...

Full description

Bibliographic Details
Main Authors: İlke Demir, Forest Hughes, Aman Raj, Kaunil Dhruv, Suryanarayana Murthy Muddala, Sanyam Garg, Barrett Doo, Ramesh Raskar
Format: Article
Language:English
Published: MDPI AG 2018-03-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:http://www.mdpi.com/2220-9964/7/3/84
_version_ 1811314327785832448
author İlke Demir
Forest Hughes
Aman Raj
Kaunil Dhruv
Suryanarayana Murthy Muddala
Sanyam Garg
Barrett Doo
Ramesh Raskar
author_facet İlke Demir
Forest Hughes
Aman Raj
Kaunil Dhruv
Suryanarayana Murthy Muddala
Sanyam Garg
Barrett Doo
Ramesh Raskar
author_sort İlke Demir
collection DOAJ
description We describe our automatic generative algorithm to create street addresses from satellite images by learning and labeling roads, regions, and address cells. Currently, 75% of the world’s roads lack adequate street addressing systems. Recent geocoding initiatives tend to convert pure latitude and longitude information into a memorable form for unknown areas. However, settlements are identified by streets, and such addressing schemes are not coherent with the road topology. Instead, we propose a generative address design that maps the globe in accordance with streets. Our algorithm starts with extracting roads from satellite imagery by utilizing deep learning. Then, it uniquely labels the regions, roads, and structures using some graph- and proximity-based algorithms. We also extend our addressing scheme to (i) cover inaccessible areas following similar design principles; (ii) be inclusive and flexible for changes on the ground; and (iii) lead as a pioneer for a unified street-based global geodatabase. We present our results on an example of a developed city and multiple undeveloped cities. We also compare productivity on the basis of current ad hoc and new complete addresses. We conclude by contrasting our generative addresses to current industrial and open solutions.
first_indexed 2024-04-13T11:09:51Z
format Article
id doaj.art-69faa616ef904da6919073e44a1325a1
institution Directory Open Access Journal
issn 2220-9964
language English
last_indexed 2024-04-13T11:09:51Z
publishDate 2018-03-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj.art-69faa616ef904da6919073e44a1325a12022-12-22T02:49:09ZengMDPI AGISPRS International Journal of Geo-Information2220-99642018-03-01738410.3390/ijgi7030084ijgi7030084Generative Street Addresses from Satellite Imageryİlke Demir0Forest Hughes1Aman Raj2Kaunil Dhruv3Suryanarayana Murthy Muddala4Sanyam Garg5Barrett Doo6Ramesh Raskar7Facebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAFacebook, 1 Hacker Way, Meenlo Park, CA 94025, USAWe describe our automatic generative algorithm to create street addresses from satellite images by learning and labeling roads, regions, and address cells. Currently, 75% of the world’s roads lack adequate street addressing systems. Recent geocoding initiatives tend to convert pure latitude and longitude information into a memorable form for unknown areas. However, settlements are identified by streets, and such addressing schemes are not coherent with the road topology. Instead, we propose a generative address design that maps the globe in accordance with streets. Our algorithm starts with extracting roads from satellite imagery by utilizing deep learning. Then, it uniquely labels the regions, roads, and structures using some graph- and proximity-based algorithms. We also extend our addressing scheme to (i) cover inaccessible areas following similar design principles; (ii) be inclusive and flexible for changes on the ground; and (iii) lead as a pioneer for a unified street-based global geodatabase. We present our results on an example of a developed city and multiple undeveloped cities. We also compare productivity on the basis of current ad hoc and new complete addresses. We conclude by contrasting our generative addresses to current industrial and open solutions.http://www.mdpi.com/2220-9964/7/3/84road extractionremote sensingsatellite imagerymachine learningsupervised learninggenerative schemesautomatic geocoding
spellingShingle İlke Demir
Forest Hughes
Aman Raj
Kaunil Dhruv
Suryanarayana Murthy Muddala
Sanyam Garg
Barrett Doo
Ramesh Raskar
Generative Street Addresses from Satellite Imagery
ISPRS International Journal of Geo-Information
road extraction
remote sensing
satellite imagery
machine learning
supervised learning
generative schemes
automatic geocoding
title Generative Street Addresses from Satellite Imagery
title_full Generative Street Addresses from Satellite Imagery
title_fullStr Generative Street Addresses from Satellite Imagery
title_full_unstemmed Generative Street Addresses from Satellite Imagery
title_short Generative Street Addresses from Satellite Imagery
title_sort generative street addresses from satellite imagery
topic road extraction
remote sensing
satellite imagery
machine learning
supervised learning
generative schemes
automatic geocoding
url http://www.mdpi.com/2220-9964/7/3/84
work_keys_str_mv AT ilkedemir generativestreetaddressesfromsatelliteimagery
AT foresthughes generativestreetaddressesfromsatelliteimagery
AT amanraj generativestreetaddressesfromsatelliteimagery
AT kaunildhruv generativestreetaddressesfromsatelliteimagery
AT suryanarayanamurthymuddala generativestreetaddressesfromsatelliteimagery
AT sanyamgarg generativestreetaddressesfromsatelliteimagery
AT barrettdoo generativestreetaddressesfromsatelliteimagery
AT rameshraskar generativestreetaddressesfromsatelliteimagery