<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">It reminds me how in 60s and 70s it was
widely believed that the computers will be doing text translation
instead of human translators. We realize now, fifty years later,
that is actually a hard problem. And it is still impossible to
translate a novel or a poem by a computer program alone.<br>
<br>
I would be very surprised if digitizing landuse from satellite
images could be done by a robot. Even an automatic extraction of
an image from a background in the product photography does not
work reliably. And it is an easier task as in product photography
it is possible to control light, background color, etc. In fact it
is mostly done manually even though there are numerous programs
and Photoshop plugins for it, which kind of work in some
circumstances.<br>
<br>
New products for product photography & e-commerce will be
appearing endlessly. But we do not have that much landuse. The
Earth surface will not be growing, and there will be no other
habitable planets in the near future. In my opinion, a human,
especially who knows the land, should be participating in mapping
landuse. <br>
<br>
But certainly, if a breakthrough happens in a self-learning neural
network technology then the situation will change, and not only in
mapping and translation; it will be a new brave world.<br>
<br>
What I would like to have however now is the better tools for
landuse & natural. For example, I would like to be able to
hide in the JOSM existing already power-lines, roads, paths, etc.
in order to map farlmland, woods, grassland, etc. Perhaps, it is
possible in JOSM, but I could not find it yet.<br>
<br>
Best regards,<br>
Oleksiy<br>
<br>
<br>
<br>
On 24.12.16 18:21, Christian Quest wrote:<br>
</div>
<blockquote
cite="mid:CAAXY6DP7R-81vHH+JJ97KG75efTxNkVVtBk3u2Aoja=bLuYwKg@mail.gmail.com"
type="cite">
<div dir="ltr">One example: OpenSolarMap...
<div><br>
</div>
<div>We first start by crowdsourcing building roof orientations
using a very simple webapp (no need to register, open to
anybody).</div>
<div>When enough contribution match they are considered OK (at
least 3 more than all other contributions).</div>
<div><br>
</div>
<div>Then, these contributions were used to train a neural
network.</div>
<div><br>
</div>
<div>Then the nueral network was used to classify other roofs...
and the result has been put back as robot contribution to the
crowdsourcing webapp counting for 1 or 2 contributions
depending on the level of confidence (raw data is also
available for download).</div>
<div><br>
</div>
<div>In all cases, there is always at least one human
contribution, before putting anything back to OSM.</div>
<div>It is also interesting to compare when human and robot do
not agree ;)</div>
<div><br>
</div>
<div>Links...</div>
<div><a moz-do-not-send="true" href="http://opensolarmap.org/">http://opensolarmap.org/</a></div>
<div><a moz-do-not-send="true"
href="https://github.com/opensolarmap">https://github.com/opensolarmap</a><br>
</div>
<div><br>
</div>
<div>Next step is to use the same technique on other kind of
challenges, like:</div>
<div>- landuse boundaries (to speedup/simplify Corine Land cover
import improvements)</div>
<div>- check road alignment with aerial imagery on "old" OSM
traced contributions</div>
<div>etc...</div>
<div><br>
</div>
<div>The potential of deep learning mixed with human
contributions can give very good things if done properly.</div>
<div><br>
</div>
</div>
<div class="gmail_extra">-- <br>
<div class="gmail_signature" data-smartmail="gmail_signature">
<div dir="ltr">Christian Quest - OpenStreetMap France</div>
</div>
</div>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
talk mailing list
<a class="moz-txt-link-abbreviated" href="mailto:talk@openstreetmap.org">talk@openstreetmap.org</a>
<a class="moz-txt-link-freetext" href="https://lists.openstreetmap.org/listinfo/talk">https://lists.openstreetmap.org/listinfo/talk</a>
</pre>
</blockquote>
<p><br>
</p>
</body>
</html>