<html><head></head><body><div class="ydpf05eae0dyahoo-style-wrap" style="font-family: verdana, helvetica, sans-serif; font-size: 13px;"><div><div>As John is saying, quality can vary a lot. You should look at the thread where I presented geometry quality analysis recently.</div><div><a href="https://lists.openstreetmap.org/pipermail/talk/2018-September/081392.html" rel="nofollow" target="_blank">https://lists.openstreetmap.org/pipermail/talk/2018-September/081392.html</a></div><div><br></div><div>You need a more rigourus procedure where you can compare AI with contributors that operate in the same conditions, with the same imagery. <br></div><br><div class="ydpf05eae0dsignature"><span style="font-style:italic;color:rgb(0, 0, 191);font-weight:bold;"> <br><font face="garamond, new york, times, serif">Pierre </font><br></span></div></div>
<div><br></div><div><br></div>
</div><div id="ydp49e595dayahoo_quoted_3126934546" class="ydp49e595dayahoo_quoted">
<div style="font-family:'Helvetica Neue', Helvetica, Arial, sans-serif;font-size:13px;color:#26282a;">
<div>
Le mardi 20 novembre 2018 09 h 44 min 59 s HNE, John Whelan <jwhelan0112@gmail.com> a écrit :
</div>
<div><br></div>
<div><br></div>
<div><div id="ydp49e595dayiv6227174310"><div><div style="font-size:12pt;font-family:Verdana;">I've done a lot of validation in HOT. Some
is done by people with little experience so I don't think validated
tiles would be much use to you. Also be aware that some imagery can be
three years out of date so the imagery can vary. The sort of problems
you'll run into are much of the HOT mapping is done by inexperienced
mappers using iD and the buildings are more approximate than you might
like especially on size and shape. It takes four times longer to
correct a building than to remap it so as a rule of thumb validators
tend to stay away from projects with buildings.<br clear="none"><br clear="none">Having said that
have a look at the hot projects for one that is 100% complete and 100%
validated. You should be able to work out the coordinates from the
project and if you are lucky it should also give you the imagery used
when mapping for HOT. Beware this OpenStreetMap and some mapping may
have taken place on the ground showing buildings etc that are not on the
image.<br clear="none"><br clear="none">You might be better off working with an experienced
mapper who can both map and check the sources. They should also check
for duplicates, there are tools available. I suggest an area that
hasn't been mapped before and map it correctly with an experienced
mapper using JOSM and things like the building_tool plugin.<br clear="none"><br clear="none">If
you're just trying the algorithm out Ottawa in Canada has accurate
buildings in OpenStreetMap.<br clear="none"><br clear="none">Have fun<br clear="none"><br clear="none">Cheerio John<br clear="none"><br clear="none"><span>Georgy
Potapov wrote on 2018-11-20 9:25 AM:</span><br clear="none"><blockquote type="cite"></blockquote></div></div><div><div class="ydp49e595dayiv6227174310yqt1060198846" id="ydp49e595dayiv6227174310yqt39263"><div dir="ltr">Dear John,<div><br clear="none"></div><div>the question isn't about
imports. Seems guys are preparing dataset to train and test models and
they need to download data that's been already validated within Missing
Maps, as a "ground truth". </div><div>Is there a way to get the precise
coordinates of the areas where this job is done or projected to be
done?</div><div>Me too was asking if it makes sense to apply algorithm
to detect damaged buildings on imagery to leverage the mapping speed in
disaster affected areas?</div><div><br clear="none"></div><div>All the best,</div><div>Georgy</div><br clear="none"><div class="ydp49e595dayiv6227174310gmail_quote"><div dir="ltr">On Tue, Nov 20, 2018 at 3:29 PM john
whelan <<a shape="rect" href="mailto:jwhelan0112@gmail.com" rel="nofollow" target="_blank">jwhelan0112@gmail.com</a>> wrote:<br clear="none"></div><blockquote class="ydp49e595dayiv6227174310gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div>Essentially you are proposing an
import. There are OpenStreetMap rules about how this should be done.
It can be done, Microsoft has released building outlines for the US
which were created in this manner but the import itself is being done in
sections by conventional mappers.<div><br clear="none"></div><div>You will need the cooperation of the local mappers on the
ground and imports of dubious quality tend to get a fair chunk of
flack. I would suggest you Google OSM imports before doing anything.</div><div><br clear="none"></div><div>Cheerio John</div></div><br clear="none"><div class="ydp49e595dayiv6227174310gmail_quote"><div dir="ltr">On Mon, 19 Nov 2018, 10:47 pm Serkan
Karakulak <<a shape="rect" href="mailto:sk7685@nyu.edu" rel="nofollow" target="_blank">sk7685@nyu.edu</a> wrote:<br clear="none"></div><blockquote class="ydp49e595dayiv6227174310gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div dir="ltr"><div dir="ltr">Hi,<div>I am a
graduate student in a Data Science program, and I wanted to get in touch
with you because me and my two other friends are interested in working
on a machine learning project to map areas using their satellite images
and produce their labels. If we obtain a high accuracy, we thought it
could be of use to the hotosm and the missingmaps initiatives.<br clear="none"></div><div><div><br clear="none"></div><div>I
have first heard about Missing Maps when I came across a mapathlon
event two years ago in Istanbul. We were in search for a class project
for one of our courses and I remembered about the mapathlon event and we
would be very happy if we could contribute to the this wonderful
initiative. There are already some previous successful works on this
subject, so we are very hopeful that we could come up with an algorithm
with high accuracy.</div><div><br clear="none"></div><div>In order to develop the
model, we need to extract bounding boxes of the validated tiles we see
at hotosm. Then we will extract the satellite images and their labels
using the label-maker API which is developed by DevSeed. Is there a
method to extract the coordinates of these validated tiles? </div><div><br clear="none"></div><div>Thank
you for your time and help.</div><div><br clear="none"></div><div>Best,</div><div><br clear="none"></div><div>Serkan</div></div></div></div>
_______________________________________________<br clear="none">
HOT mailing list<br clear="none">
<a shape="rect" href="mailto:HOT@openstreetmap.org" rel="nofollow" target="_blank">HOT@openstreetmap.org</a><br clear="none">
<a shape="rect" href="https://lists.openstreetmap.org/listinfo/hot" rel="nofollow" target="_blank">https://lists.openstreetmap.org/listinfo/hot</a><br clear="none"></blockquote></div>
_______________________________________________<br clear="none">
HOT mailing list<br clear="none">
<a shape="rect" href="mailto:HOT@openstreetmap.org" rel="nofollow" target="_blank">HOT@openstreetmap.org</a><br clear="none">
<a shape="rect" href="https://lists.openstreetmap.org/listinfo/hot" rel="nofollow" target="_blank">https://lists.openstreetmap.org/listinfo/hot</a><br clear="none"></blockquote></div></div></div><br clear="none"><div class="ydp49e595dayiv6227174310moz-signature">-- <br clear="none">
<div>Sent from <a shape="rect" href="https://www.postbox-inc.com/?utm_source=email&utm_medium=siglink&utm_campaign=reach" rel="nofollow" target="_blank"><span style="color:rgb(0, 157, 247);">Postbox</span></a></div></div></div></div><div class="ydp49e595dayqt1060198846" id="ydp49e595dayqt98804">_______________________________________________<br clear="none">HOT mailing list<br clear="none"><a shape="rect" href="mailto:HOT@openstreetmap.org" rel="nofollow" target="_blank">HOT@openstreetmap.org</a><br clear="none"><a shape="rect" href="https://lists.openstreetmap.org/listinfo/hot" rel="nofollow" target="_blank">https://lists.openstreetmap.org/listinfo/hot</a><br clear="none"></div></div>
</div>
</div></body></html>