<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Feb 3, 2017 at 3:07 PM, Moritz Lennert <span dir="ltr"><<a href="mailto:mlennert@club.worldonline.be" target="_blank">mlennert@club.worldonline.be</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">On 03/02/17 14:06, Rashad Kanavath wrote:<br>
</span><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">
<br>
<br>
On Wed, Jan 25, 2017 at 11:22 AM, Moritz Lennert<br></span><div><div class="h5">
<<a href="mailto:mlennert@club.worldonline.be" target="_blank">mlennert@club.worldonline.be</a> <mailto:<a href="mailto:mlennert@club.worldonline.be" target="_blank">mlennert@club.worldonl<wbr>ine.be</a>>> wrote:<br>
<br>
On 24/01/17 20:40, Raphael Knevels wrote:<br>
<br>
Thanks for the quick response :-)<br>
<br>
The extent of my region is also the extent of my imagery-group.<br>
For i.segment I used as memory 10240 MB with a threshold of 0.25.<br>
<br>
<br>
That's a pretty large threshold which generally leads to<br>
under-segmentation. You might want to start with a value closer to 0.01.<br>
<br>
<br>
In SAGA I used at first Seed Generation (Band Width of 18, but I<br>
also<br>
varied this parameter) for producing the Seed Output. The Seed<br>
Output is<br>
a raster with floating point values. Moreover, the Seed Output<br>
contains<br>
single pixels distributed over the hole area. The "space"<br>
between those<br>
pixels is "no data". The segmentation is then computed by Seeded<br>
Region<br>
Growing with the seed grid as input.<br>
<br>
"Seeds in i.segment have to be polygons not points. These polygons<br>
are<br>
represented by identical positive integer values (= IDs) in adjacent<br>
pixels, and they have to cover the entire region. When used as<br>
seeds for<br>
a segmentation, these polygons are the further merged."<br>
<br>
<br>
Sorry, but this was actually wrong information from my part:<br>
i.segment also supports seed pixels. From the man page:<br>
<br>
"The seeds map can be used to provide either seed pixels (random or<br>
selected points from which to start the segmentation process) or<br>
seed segments. If the seeds are the results of a previous<br>
segmentation with lower threshold, hierarchical segmentation can be<br>
performed. The different approaches are automatically detected by<br>
the program: any pixels that have identical seed values and are<br>
contiguous will be assigned a unique segment ID. "<br>
<br>
<br>
However, the seed map has to have integer values. To get that from<br>
you SAGA output (floating-point) seed map, just run r.clump.<br>
<br>
-> alright. That means, I definitely must convert the no data<br>
values in the SAGA Seed Output to zero or any other integer number.<br>
<br>
<br>
No, I actually don't think this would help in any way as this would<br>
create one big region out of all the no data pixels...<br>
<br>
Meanwhile, I also tried the segmentation result of SAGA Seeded<br>
Region Growing as Seeds for GRASS - this works...<br>
<br>
<br>
And how long did this take ?<br>
<br>
" You could try using the brand new i.superpixels.slic add-on to<br>
create superpixels which you can then use as seeds."<br>
-> I could successfully install and open it ("g.extension<br>
i.superpixels.slic", GRASS 7.2.0).<br>
However, when I run the tool with default settings, GRASS gives<br>
a problem message and finishs the process.<br>
<br>
<br>
Ok, this sounds like bug #3247 [1] for which the author hasn't<br>
applied the fix, yet. Rashad, will you have the opportunity to apply<br>
just the fix for the actual bug (not necessarily the other proposals<br>
in the patch), soon, or should I do it ?<br>
<br>
<br>
I had pushed fix for compile error ( min and max ). Is it the same error?<br>
</div></div></blockquote>
<br>
No, it was the error explained in #3247. But the issue was fixed and since then MarkusM has significantly build upon your work on i.superpixels.slic. We now have a nicely functioning module. Thank you for your great work on this !<span class="HOEnZb"><font color="#888888"><br></font></span></blockquote><div><br></div><div>Sorry. I saw that later. l SLICO and other options needs to be added I think.<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="HOEnZb"><font color="#888888">
<br>
Moritz<br>
</font></span></blockquote></div><br><br clear="all"><br>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div><font face="arial, helvetica, sans-serif">Regards,<br> Rashad</font></div></div>
</div></div>