<html>
<head>
<meta http-equiv="Content-Type" content="text/html;
charset=windows-1252">
</head>
<body>
<div class="moz-cite-prefix">Le 06/10/2020 à 22:41, Nick Whitelegg a
écrit :<br>
</div>
<blockquote type="cite"
cite="mid:DBAPR07MB6807C406E03869CCBB134439A60D0@DBAPR07MB6807.eurprd07.prod.outlook.com">
<meta http-equiv="Content-Type" content="text/html;
charset=windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
Hi,</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
Apologies if this is only tangentially OSM related, but I
thought I'd ask here to try and get some expert advice.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
As you may know, Mapillary has been bought by Facebook and there
has been interest in developing, or at least starting to
develop/actively researching the possibility of, some sort of
open source alternative. I have been developing OpenTrailView
(opentrailview.org), however I now have a collaborator to work
on exploring an open source panos platform.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
The main question I have relates to the very necessary privacy
steps that must be taken, in particular face and license plate
blurring. I have experimented with various libraries using
various datasets and models, and have found that the
understand.ai Anonymizer (<a
href="https://github.com/understand-ai/anonymizer"
id="LPlnk468277" moz-do-not-send="true">https://github.com/understand-ai/anonymizer</a>),
which advertises itself as something specifically aimed at
implementing the privacy protections needed to comply with the
GDPR, seems to be working the best.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
It detects faces and license plates in clear view on panoramas,
which can then be blurred.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
My question, then, is what to do about people, or cars, which
are further away from the camera? In these cases, the algorithm
does not necessarily detect the face or license plate, but on
the other hand in general the faces and license plates are not
clearly visible, or identifiable, in any case.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
So in summary, the tool blurs clearly visible faces or license
plates, but in general does not blur those which are not clearly
visible.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
Apologies once again that this is only tangentially related to
OSM (OpenTrailView uses OSM to connect panos together, so not
completely unrelated) but it is very much an open geodata issue,
so I thought I'd ask to get feedback.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif;
font-size: 12pt; color: rgb(0, 0, 0);">
I am in the UK and the server is in Germany (Hetzner), so GDPR
would apply.</div>
<div>
<div id="Signature">
<div id="divtagdefaultwrapper" dir="ltr" style="color: rgb(0,
0, 0);">
<p style="font-family: Calibri, Arial, Helvetica,
sans-serif; font-size: 12pt; margin-top: 0px;
margin-bottom: 0px;">
</p>
<div style="font-family: Calibri, Arial, Helvetica,
sans-serif; font-size: 12pt; margin: 0px;">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica,
sans-serif; font-size: 12pt; margin: 0px;">
Thanks,</div>
<div style="font-family: Calibri, Arial, Helvetica,
sans-serif; font-size: 12pt; margin: 0px;">
Nick</div>
</div>
</div>
</div>
</blockquote>
<p><br>
</p>
<p>We have tested blurring using image segmentation which allows to
blur full parts of pictures like people and cars, not only faces
and license plates.</p>
<p><br>
</p>
<p>Here is the result:
<a class="moz-txt-link-freetext" href="https://takeitout.cquest.org/photo/cquest/blurred/">https://takeitout.cquest.org/photo/cquest/blurred/</a></p>
<p><br>
</p>
<p>The code used is on github:
<a class="moz-txt-link-freetext" href="https://github.com/tyndare/blur-persons/">https://github.com/tyndare/blur-persons/</a></p>
<p><br>
</p>
<p>We did some tests using TPU to speedup the process.</p>
<p><br>
</p>
<pre class="moz-signature" cols="72">--
Christian Quest - OpenStreetMap France</pre>
</body>
</html>