<div dir="ltr">Hello everyone<div><br></div><div>Continuing the previous discussion, I would like to propose something and the community's suggestions are welcomed/needed. I can understand that this thread is a little old, so let me remind you that its regarding the automatic geo-referencer idea. The idea is also proposed on the GDAL ideas page (<a href="http://trac.osgeo.org/gdal/wiki/SummerOfCode">http://trac.osgeo.org/gdal/wiki/SummerOfCode</a>). </div>
<div><br></div><div>Based on the previous discussions, what came out was that we can improve the current implementation of SIMPLE SURF in GDAL which was developed as a part of 2012 GSOC GDAL Correlator project, to support <b>large data</b> and <b>multi spectral imagery</b>. And then apply this <b>modified</b> algorithm for the geo-reference purposes. Now I have been in touch with Chaitanya, who is willing to mentor this project, and there are some things on which we would like to know community's suggestions/response.</div>
<div><br></div><div>There are basically two things that can be done regarding this project:</div><div><br></div><div>1. As mentioned above, we can modify the SIMPLE SURF algorithm and make it much better for the geo-reference purposes. Already, a lot had been discussed on this and we have a fairly good idea about what is to be done.</div>
<div><br></div><div>2. One more thing that can be done is that we can implement BRISK algorithm[1] instead of SURF along with the FLANN matcher for this purpose. What advantages this thing offers is that it is fairly fast and gives comparable outputs along with that it works well with fairly large data sets. So we do not need to segment the imagery as we would have done in the case of SURF. Also added to this, this algorithm also has no patent issues. We had a lot of problem regarding patent issues in SIFT/SURF and we discussed them at length on the mailing list as well. </div>
<div><br></div><div>One thing that I fell can be done is that two proposal can be written, one for each and then community can decide accordingly which one is more useful. Or we can decide it here itself..? </div><div><br>
</div><div>Kindly provide your valuable comments and suggestion..</div><div><br></div><div>With Regards,</div><div class="gmail_extra"><br clear="all"><div><div dir="ltr"><blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
Kshitij Kansal</blockquote><blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">Lab For Spatial Informatics,<br></blockquote><blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
IIIT Hyderabad<br><br></blockquote></div></div>
1. <a href="http://www.robots.ox.ac.uk/~vgg/rg/papers/brisk.pdf">http://www.robots.ox.ac.uk/~vgg/rg/papers/brisk.pdf</a><br><br><div class="gmail_quote">On Thu, Feb 13, 2014 at 2:23 PM, Kshitij Kansal <span dir="ltr"><<a href="mailto:kansal.k@gmail.com" target="_blank">kansal.k@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><div dir="ltr"><div><div>Hello Everyone<br><br></div>I have updated the Summer Of Code Ideas Page for GDAL. I have Introduced the above idea in that page also. Mr. Chaitanya Kumar is willing to mentor the project.<br>
</div>
<div><br>Please look into this.<br><br></div><div>Suggestions and Comments are welcomed.<br><br></div><div>Regards,<br></div><div class="gmail_extra"><div class=""><br clear="all"><div><div dir="ltr"><blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
Kshitij Kansal</blockquote><blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">Lab For Spatial Informatics,<br></blockquote><blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
IIIT Hyderabad<br></blockquote></div></div>
<br><br></div><div class="gmail_quote"><div class="">On Sat, Feb 8, 2014 at 2:07 PM, Dmitriy Baryshnikov <span dir="ltr"><<a href="mailto:bishop.dev@gmail.com" target="_blank">bishop.dev@gmail.com</a>></span> wrote:<br>
</div><div><div class="h5"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<div text="#000000" bgcolor="#FFFFFF">
<div>Hi,<br>
<br>
Even note that you cannot get the code from this projects and
merge it to GDAL, but you free to develop you own implementation
of this algorithms as path of GDAL.<br>
This is a same situation with correlator. Andrew cannot get code
from OpenCV and GRASS as incompatible licenses, so the own
(simple) implementation was provided.<br>
One can change this implementation to be more advanced: support
large datasets, more bands, etc. Everybody welcome to do it.<br>
<pre cols="72">Best regards,
Dmitry</pre>
08.02.2014 2:15, Kshitij Kansal пишет:<br>
</div><div><div>
<blockquote type="cite">
<div dir="ltr">Sir
<div><br>
</div>
<div>I am providing the links for both the algorithms that I
talked. I am new to this licence issues thing so I would be
highly grateful if you can clarify doubts and if can proceed
on working for this idea.</div>
<div><br>
</div>
<div><a href="http://www.cs.ubc.ca/%7Elowe/keypoints/" target="_blank">http://www.cs.ubc.ca/~lowe/keypoints/</a> (SIFT)<br>
</div>
<div><a href="http://www.ipol.im/pub/art/2011/my-asift/" target="_blank">http://www.ipol.im/pub/art/2011/my-asift/</a> (ASIFT)
[here source code is provided. It contains license ]<br>
</div>
<div><a href="http://www.cmap.polytechnique.fr/%7Eyu/research/ASIFT/demo.html" target="_blank">http://www.cmap.polytechnique.fr/~yu/research/ASIFT/demo.html</a> (Demo
Page for ASIFT)<br>
</div>
<div><br>
</div>
<div>The SIFT algorithm in itself is patented. They only provide
binaries. I am not sure If we can use those binaries or not.</div>
<div>As far as ASIFT is concerned, i think its implementation is
only patented. </div>
<div><br>
</div>
<div>Kindly clarify this.</div>
<div><br>
</div>
<div>Thanking You</div>
<div>With Regards,<br>
</div>
<div class="gmail_extra">
<br clear="all">
<div>
<div dir="ltr">
<blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">Kshitij
Kansal</blockquote>
<blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">Lab
For Spatial Informatics,<br>
</blockquote>
<blockquote style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">IIIT
Hyderabad<br>
</blockquote>
</div>
</div>
<br>
<br>
<div class="gmail_quote">On Sat, Feb 8, 2014 at 2:23 AM, Even
Rouault <span dir="ltr"><<a href="mailto:even.rouault@mines-paris.org" target="_blank">even.rouault@mines-paris.org</a>></span>
wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<div>Selon Kshitij Kansal <<a href="mailto:kansal.k@gmail.com" target="_blank">kansal.k@gmail.com</a>>:<br>
<br>
Kshitij,<br>
<br>
I'm surprised that you mention licenses<br>
for algorithms. What are your sources for that?<br>
Only *implementations* can be licensed<br>
not algorithms themselves. So if you<br>
develop your own implementation you are free<br>
to select the license you wish. There<br>
might be issues linked to potential pattents<br>
in some countries but that is acceptable in my opinion<br>
as software parents are not valid in all contries<br>
so mentionning potential issues with them<br>
in the documentation is sufficient .<br>
<br>
> Hello<br>
><br>
> Based on all suggestion<br>
</div>
<div>ins and comments above, I have come up
with one thing.<br>
><br>
> The most important thing that could have been a
road block for this project<br>
> was licence issues which was pointed by Even
Rouault.<br>
><br>
> I am interested in implementing the SIFT or ASIFT
algorithms for automatic<br>
> geo-referencing which I proposed in above mails. I
am interested in making<br>
> a separate tool which will be completely based on
the GDAL and maintained<br>
> by GDAL community. I looked into the
GDAL-correlator idea which was also<br>
</div>
> implemented as a part of GSoC. That idea uses only
*SIMPLE SURF *algorithm<br>
> for control point detection and is only *limited to
small size three band<br>
> imagery(RGB)*.<br>
<div>><br>
> I am interested in developing something that is
fully automated and works<br>
> on large multi band imagery.But the above two
algorithms that I am planning<br>
> to use come up with the licence that does not
allows the free use for<br>
</div>
<div>> commercial purposes. The free use of
above algorithm are restricted to *"non<br>
> profit research and non profit educational
purposes"*(in case of<br>
> ASIFT) and *"research<br>
</div>
> purposes only" *(in case of SIFT).<br>
<div>
<div>><br>
> This means that the final product as a result of
this product will also be<br>
> bounded by the above licences. It can not go into
GDAL's main distribution<br>
> but can be used as a separate utility of GDAL for
non-commercial uses only.<br>
> Basically the commercial use of the tool won't be
allowed without approval<br>
> from the concerned people.<br>
><br>
> Your views and suggestions are highly
appreciated.<br>
><br>
> Regards,<br>
><br>
> Kshitij Kansal<br>
><br>
> Lab For Spatial Informatics,<br>
><br>
> IIIT Hyderabad<br>
><br>
><br>
><br>
> On Thu, Jan 30, 2014 at 12:25 PM, Kshitij Kansal
<<a href="mailto:kansal.k@gmail.com" target="_blank">kansal.k@gmail.com</a>>
wrote:<br>
><br>
> > Hello<br>
> ><br>
> > @Jukka Rahkonen: The OSSIM project (the link
you provided) is more of<br>
> > image orthorectification. Although<br>
> > they are doing image co-registration but its
as one of the steps of<br>
> > orthorectification(I could only understand
this from the manual).<br>
> > Also I am not sure of the techniques they
are using for this purposes.<br>
> > (Its written corner point detection but
How?)<br>
> > I am new to OSSIM, so not aware of this
thing's functionality and<br>
> > accuracy. I am in the process of estimating
it.<br>
> ><br>
> > Thank you for pointing this out.<br>
> ><br>
> > Coming to the Frank Warmerdam's blog (<a href="http://fwarmerdam.blogspot.fi/" target="_blank">http://fwarmerdam.blogspot.fi/</a>).<br>
> > Here the author is talking about writing a
code for converting the GCP's<br>
> > into RPC's. But the next question comes is
where is he getting GCP's from.<br>
> > Now this is the part where I aim to work on
and improve.<br>
> ><br>
> > Given two images, if we can automatically
extract GCP's from them then we<br>
> > are in a way speeding up and automating this
whole process. Once we have<br>
> > GCP, there are a lot of things that we can
do from them like<br>
> > geo-referencing(which I plan on doing),
image stitching etc.<br>
> ><br>
</div>
</div>
> > *Also you talked about a "more light weighted
system". Can you please<br>
> > elaborate on this?* I could not understand what
you actually meant from<br>
<div>> > that.<br>
> ><br>
> > If we look into the last year idea's page (<br>
> > <a href="http://trac.osgeo.org/gdal/wiki/SummerOfCode" target="_blank">http://trac.osgeo.org/gdal/wiki/SummerOfCode</a>),
there is one idea that is<br>
> > proposed regarding the "Raster/Vector
geo-referencer on the Web". I want to<br>
> > modify this idea a little bit and want to
automate the whole process. As<br>
> > far as the automation is concerned, we can
develop GDAL functions for<br>
> > that(which will be completely re-usable) and
then developing a Web based<br>
> > geo-referencer would only require calling
those functions.<br>
> ><br>
</div>
> > If we do this thing,* two objectives will be
fulfilled*.* First*, GDAL<br>
> > will get a web based geo-referencer. *Secondly*,
communities that use<br>
<div>
<div>> > GDAL and have not developed
these kind of geo-referencer(Like QGIS) can<br>
> > directly use the functions developed and
then build on that.<br>
> ><br>
> > Suggestions and comments are welcomed.<br>
> ><br>
> > Thank you for your propositions.<br>
> ><br>
> > Regards,<br>
> ><br>
> > Kshitij Kansal<br>
> ><br>
> > Lab For Spatial Informatics,<br>
> ><br>
> > IIIT Hyderabad<br>
> ><br>
> ><br>
> ><br>
> > On Wed, Jan 29, 2014 at 1:27 PM, Jukka
Rahkonen <<a href="mailto:jukka.rahkonen@mmmtike.fi" target="_blank">jukka.rahkonen@mmmtike.fi</a><br>
> > > wrote:<br>
> ><br>
> >> Kshitij Kansal <kansal.k <at> <a href="http://gmail.com" target="_blank">gmail.com</a>> writes:<br>
> >><br>
> >> ><br>
> >> > Even,<br>
> >> > Thank you for pointing out this
issue. I will keep this in mind.<br>
> >> ><br>
> >> > I will look into that last year
project and try to understand the<br>
> >> implementation.<br>
> >> ><br>
> >><br>
> >> > More suggestions and comments are
always welcomed.<br>
> >><br>
> >> Hi,<br>
> >><br>
> >> Another OSGeo project OSSIM has
implemented an automatic image to image<br>
> >> rectification. Isn't that a bit alike
your plan?<br>
> >> <a href="http://download.osgeo.org/ossim/docs/OSSIM_Coregistration_UserManual.pdf" target="_blank">http://download.osgeo.org/ossim/docs/OSSIM_Coregistration_UserManual.pdf</a><br>
> >><br>
> >> Frank Warmerdam seems to entertain
himself with something related<br>
> >> <a href="http://fwarmerdam.blogspot.fi/" target="_blank">http://fwarmerdam.blogspot.fi/</a><br>
> >><br>
> >> This article from 2013 may also give
some inspiration<br>
> >><br>
> >><br>
><br>
<a href="http://www.academia.edu/4388853/OrientAL_-_Automatic_geo-referencing_and_ortho-rectification_of_archaeological_aerial_photographs" target="_blank">http://www.academia.edu/4388853/OrientAL_-_Automatic_geo-referencing_and_ortho-rectification_of_archaeological_aerial_photographs</a><br>
> >><br>
> >> All these three aim to very high quality
and I am sure that there is also<br>
> >> need for a more light-weight system.<br>
> >><br>
> >> -Jukka Rahkonen-<br>
> >><br>
> >>
_______________________________________________<br>
> >> gdal-dev mailing list<br>
> >> <a href="mailto:gdal-dev@lists.osgeo.org" target="_blank">gdal-dev@lists.osgeo.org</a><br>
> >> <a href="http://lists.osgeo.org/mailman/listinfo/gdal-dev" target="_blank">http://lists.osgeo.org/mailman/listinfo/gdal-dev</a><br>
> >><br>
> ><br>
> ><br>
><br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
</div>
</div>
</blockquote>
</div>
<br>
</div>
</div>
<br>
<fieldset></fieldset>
<br>
<pre>_______________________________________________
gdal-dev mailing list
<a href="mailto:gdal-dev@lists.osgeo.org" target="_blank">gdal-dev@lists.osgeo.org</a>
<a href="http://lists.osgeo.org/mailman/listinfo/gdal-dev" target="_blank">http://lists.osgeo.org/mailman/listinfo/gdal-dev</a></pre>
</blockquote>
<br>
</div></div></div>
<br>_______________________________________________<br>
gdal-dev mailing list<br>
<a href="mailto:gdal-dev@lists.osgeo.org" target="_blank">gdal-dev@lists.osgeo.org</a><br>
<a href="http://lists.osgeo.org/mailman/listinfo/gdal-dev" target="_blank">http://lists.osgeo.org/mailman/listinfo/gdal-dev</a><br></blockquote></div></div></div><br></div></div>
</blockquote></div><br></div></div>