Title: Exploiting deep learning and volunteered geographic information for mapping buildings in Kano, Nigeria

Journal Article · · Scientific Data
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [2]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Tennessee, Knoxville, TN (United States)
+ Show Author Affiliations

Buildings in the developing world are inadequately mapped. Lack of such critical geospatial data adds unnecessary challenges to locating and reaching a large segment of the world’s most vulnerable population, impeding sustainability goals ranging from disaster relief to poverty reduction. Use of volunteered geographic information (VGI) has emerged as a widely accepted source to fill such voids. Despite its promise, availability of building maps for developing countries significantly lags behind demand. We present a new approach, coupling deep convolutional neural networks (CNNs) with VGI for automating building map generation from high-resolution satellite images for Kano state, Nigeria. Specifically, we trained a CNN with VGI building outlines of limited quality and quantity and generated building maps for a 50,000 km2 area. Resulting maps are in strong agreement with existing settlement maps and require a fraction of the manual input needed for the latter. The VGI-based maps will provide support across multiple facets of socioeconomic development in Kano state, and demonstrates potential advancements in current mapping capabilities in resource constrained countries.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
Bill and Melinda Gates Foundation; USDOE
Grant/Contract Number:
AC05-00OR22725
OSTI ID:
1607293
Journal Information:
Scientific Data, Journal Name: Scientific Data Journal Issue: 1 Vol. 5; ISSN 2052-4463
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (27)

Deep learning journal May 2015
Erratum: Corrigendum: Dermatologist-level classification of skin cancer with deep neural networks journal June 2017
A review of volunteered geographic information quality assessment methods journal May 2016
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters conference June 2016
Ready or Not, Here We Go journal June 2016
Kano, Nigeria Building Detection dataset January 2018
Citizens as sensors: the world of volunteered geography journal November 2007
Automatic discrimination of human hematopoietic tumor cell lines using a combination of imaging flow cytometry and convolutional neural network journal February 2021
Census-independent population mapping in northern Nigeria journal January 2018
Human-level control through deep reinforcement learning journal February 2015
Deep learning journal May 2015
Mastering the game of Go with deep neural networks and tree search journal January 2016
Dermatologist-level classification of skin cancer with deep neural networks journal January 2017
Researching Volunteered Geographic Information: Spatial Data, Geographic Research, and New Social Practice journal May 2012
A review of volunteered geographic information quality assessment methods journal May 2016
Hypercolumns for object segmentation and fine-grained localization conference June 2015
Fully convolutional networks for semantic segmentation conference June 2015
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters conference June 2016
A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results journal October 2013
Urban Footprint Processor—Fully Automated Processing Chain Generating Settlement Masks From Global Data of the TanDEM-X Mission journal November 2013
Dense Semantic Labeling of Subdecimeter Resolution Images With Convolutional Neural Networks journal February 2017
Learning Building Extraction in Aerial Scenes with Convolutional Networks journal November 2018
Learning to count buildings in diverse aerial scenes
  • Yuan, Jiangye; Cheriyadat, Anil M.
  • Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems - SIGSPATIAL '14 https://doi.org/10.1145/2666310.2666389
conference January 2014
Dense semantic labeling of subdecimeter resolution images with convolutional neural networks text January 2017
Deep Learning text January 2018
Kano, Nigeria Building Detection dataset January 2018
Kano, Nigeria Building Detection dataset January 2018

Cited By (6)

An overview of GeoAI applications in health and healthcare journal May 2019
Population Mapping in Informal Settlements with High-Resolution Satellite Imagery and Equitable Ground-Truth preprint January 2020
The impact of seasonality on multi-scale feature extraction techniques journal January 2019
An overview of GeoAI applications in health and healthcare journal May 2019
Principles and Applications of the Global Human Settlement Layer as Baseline for the Land Use Efficiency Indicator—SDG 11.3.1 journal February 2019
Mapping Human Settlements with Higher Accuracy and Less Volunteer Efforts by Combining Crowdsourcing and Deep Learning journal July 2019

Linked Research (4)

Similar Records

Related Subjects

99 GENERAL AND MISCELLANEOUS
Databases
Developing world
Geography