<div dir="ltr"><div>Sounds good to me - should have no false positives then unlike machine learning / image recognition approaches. I look forward to seeing the MapRoulette task set up. Any idea when this might be? Entirely selfish question as I want to make sure I am free when it happens otherwise I might not get a chance to participate given how quickly the last task was completed!! :-)<br></div><div><br></div><div>Thanks,<br></div><div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><span style="color:rgb(0,0,255)"><b>Rob</b></span><br></div></div></div></div></div><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, 17 Jan 2023 at 18:38, Marjan Van de Kauter <<a href="mailto:Marjan.VanDeKauter@tomtom.com">Marjan.VanDeKauter@tomtom.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div class="msg2700420376625980144">
<div style="overflow-wrap: break-word;" lang="NL-BE">
<div class="m_2700420376625980144WordSection1">
<p class="MsoNormal"><span lang="EN-US">Hi Rob,<br>
<br>
We identified the missing highway leads by spatially comparing TomTom’s in-house road centerlines with the OSM road network, and validating the results using the available imagery sources. We did not make use of machine learning or image recognition.<br>
<br>
Hope this helps!<br>
<br>
Marjan<u></u><u></u></span></p>
<p class="MsoNormal"><span lang="EN-US"><u></u> <u></u></span></p>
<div>
<div style="border-color:rgb(225,225,225) currentcolor currentcolor;border-style:solid none none;border-width:1pt medium medium;padding:3pt 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US">From:</span></b><span lang="EN-US"> Rob Nickerson <<a href="mailto:rob.j.nickerson@gmail.com" target="_blank">rob.j.nickerson@gmail.com</a>>
<br>
<b>Sent:</b> Saturday 14 January 2023 0:24<br>
<b>To:</b> Talk-GB <<a href="mailto:talk-gb@openstreetmap.org" target="_blank">talk-gb@openstreetmap.org</a>><br>
<b>Subject:</b> Re: [Talk-GB] MapRoulette challenge to connect isolated highways<u></u><u></u></span></p>
</div>
</div>
<p class="MsoNormal"><span lang="EN-US"><u></u> <u></u></span></p>
<table style="width:0.9%" width="0%" cellspacing="0" cellpadding="0" border="0" align="left">
<tbody>
<tr>
<td style="width:7.8pt;background:rgb(234,234,234);padding:5.25pt 3.75pt" width="10">
</td>
</tr>
</tbody>
</table>
<div>
<div>
<div>
<p class="MsoNormal"><span lang="EN-US">>Would you also be interested in some leads for highways that are missing from the map?<u></u><u></u></span></p>
</div>
<div>
<p class="MsoNormal"><span lang="EN-US"><u></u> <u></u></span></p>
</div>
<div>
<p class="MsoNormal">Sure. No harm in having a look at these. Based on experience there are a lot of false negatives in this sort of exercise but we can take a look :-)<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">It would be useful if you could describe where the data has come from. For example is it from machine learning / image recognition or from GPS trace data?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Thanks,<u></u><u></u></p>
</div>
<div>
<div>
<div>
<div>
<div>
<p class="MsoNormal"><b><span style="color:blue">Rob</span></b><u></u><u></u></p>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div></blockquote></div>