AI-assisted mapping of for OSM

Anna Zanchetta

The Alan Turing Institute

HOT Humanitarian OpenStreetMap Team

09/18/2024

Introduction

fAIr

https://fair-dev.hotosm.org/

RGB from OAM








Open Aerial Map

Labels from OSM








Preprocessing fAIr website

How accurate is fAIr in detecting buildings

in different conditions?

Metrics

Source: https://metrics-reloaded.dkfz.de/metric-library

Metrics

Source: https://metrics-reloaded.dkfz.de/metric-library

Dataset

Locations

Degree of urbanity

Rural

Desa Kulaba

[Indonesia]

Peri-urban

Ggaba

[Uganda]

Urban

Bogota

[Colombia]

Refugee camp

Kakuma

[Kenya]

Roof cover type

Shingles

Silvania

[Brasil]

Metal

Ngaoundere

[Cameroon]

Cement

Melbourne

[Australia]

Mixed

Kutupalong

[Bangladesh]

Urban density

Dense

Montevideo

[Uruguay]

Sparse

Gornja Rijeka

[Croatia]

Grid

Quincy

[USA]

Results

Urbanity

Roof type

Density

Banyuwangi

[Indonesia]

Banyuwangi

[Indonesia]

Banyuwangi

[Indonesia]

Banyuwangi

[Indonesia]

Pallaby, Dhaka

[Bangladesh]

Pallaby, Dhaka

[Bangladesh]

Pallaby, Dhaka

[Bangladesh]

Pallaby, Dhaka

[Bangladesh]

Denver

[USA]

Denver

[USA]

Pergamino

[Argentina]

Pergamino

[Argentina]

Kakuma

[Kenya]

Kakuma

[Kenya]

THANK YOU

Code https://github.com/ciupava/fAIr-utilities
fAIr website https://fair.hotosm.org/
Link to this presentation