On 11/01/2020 12:41, Rob Nickerson wrote:
In JOSM add it using:
wmts:https://api.mapbox.com/styles/v1/robjn/ck59jksa71nym1co31kr8mulb/wmts?access_token=pk.eyJ1Ijoicm9iam4iLCJhIjoid0dYNkY1QSJ9.A-0lzQOawGYICYPfURsjDA
And in iD Editor add it using:
Hi all,
A quick update on the MapWithAI stuff. Kaart have developed a plugin for
JOSM:
https://www.openstreetmap.org/user/the_node_less_traveled/diary/391863
https://josm.openstreetmap.de/wiki/Help/Plugin/MapWithAI
Also, but slightly less relevant now, I have thrown this data into Mapbox
studio
Thank you Andy, have commented, waiting to see if they respond.
Phil (trigpoint)
On Sunday, 5 January 2020, Andy Townsend wrote:
> On 05/01/2020 21:33, Philip Barnes wrote:
> > I have just come across an armchair edit using Facebook AI data.
> >
> > They do seem to have failed to check that
On 05/01/2020 21:33, Philip Barnes wrote:
I have just come across an armchair edit using Facebook AI data.
They do seem to have failed to check that detections are accurate, or
lack experience to identify common Midlands farmland features. They
have mapped several hedges as tracks.
The
I have just come across an armchair edit using Facebook AI data.
They do seem to have failed to check that detections are accurate, or
lack experience to identify common Midlands farmland features. They
have mapped several hedges as tracks.
Something I think we need to watch out for, this tech is
I was wondering if it was worth creating a wiki page to provide more of
these examples. Clearly the value of the data and types of false positives
vary across the country.
Jerry
On Sun, 5 Jan 2020 at 15:12, Russ Garrett wrote:
> Given the obvious flaws in the data, I'm actually quite surprised
I'm using QGiS 3.4 on a laptop with 8 Gb, but I'm sure much less will work
fine. Will send data separately.
I'm not sure Facebook have corrected for offsets in imagery so whereas the
topology may be better positioning may be worse. One of the simple quick
wins from using ML on imagery could be
On Sun, 2020-01-05 at 15:02 +, Rob Nickerson wrote:
> Thanks Jerry.
>
> I'd also subsequently discovered the data dump but had not yet got
> around to looking at it. What are you using here to view and work
> with the data? Is QGIS and 6GB RAM sufficient?
>
> I would be interested in
Given the obvious flaws in the data, I'm actually quite surprised how
good it is at spotting unmapped service roads in London - including
those which pass beneath buildings. Most of them probably deserve a
survey though.
Russ
On Sun, 5 Jan 2020 at 15:04, Rob Nickerson wrote:
>
> Thanks Jerry.
>
Thanks Jerry.
I'd also subsequently discovered the data dump but had not yet got around
to looking at it. What are you using here to view and work with the data?
Is QGIS and 6GB RAM sufficient?
I would be interested in Warwickshire if you can extract that.
And yes, we probably are not expecting
Perhaps more useful is that one can download the UK data as a geopackage
from
https://github.com/facebookmicrosites/Open-Mapping-At-Facebook/wiki/Available-Countries.
It's 147Mb zipped in a tar which unpacked is around 400Mb.
I've had a very quick look and notice quite a few concentrations of
Hi all,
I just spotted that Facebook have pushed an update to their map with AI
project:
"For our final release of 2019, we have released 84 new countries for our
AI road data with new coverage in the remainder of Europe, Asia, and
Oceania! AI roads are now available nearly globally."
Source:
12 matches
Mail list logo
