Skip to main content


#openbuildings dataset released by Google is really impressive.

I'm curious why it hasn't been a big fuzz for the #geospatial people #deeplearning #remotesensing

It has been published under open licenses #odbl and #CCby4, choose your flavor.
https://sites.research.google/open-buildings/#explore
This entry was edited (1 year ago)
in reply to Raúl Nanclares 🍜

if I would have to guess: most #geospatial enthusiasts like to explore new datasets starting in their familiar neighborhoods. Since this dataset focuses on the global south, most of the usual suspects unfortunately don't have a personal connection to the covered areas

"V1 covered Africa, in v2 we expanded to South and South-East Asia and in the current version v3 detections from Latin America and the Caribbean are also included."

#GISChat
in reply to Anita Graser 🇪🇺🇺🇦🇬🇪

That's sad, because they're missing out. This is such an improvement over Microsoft's buildings dataset.

The impacts it's going to have in the region (hate the global south expression) will be huge.

Openstreetmap could benefit from this so much.
This entry was edited (1 year ago)
in reply to Raúl Nanclares 🍜

Finally, I downloaded the buildings for one municipality in El Salvador and the dataset is quite accurate indeed ... thanks for sharing.
in reply to Metzi 🌱

@metzi
Nice! I was wondering which was the easiest way to process it.

This website uses cookies to recognize revisiting and logged in users. You accept the usage of these cookies by continue browsing this website.