<div dir="ltr"><div>I had good results including texture as an input for Sentinel-2 image classification.</div><div>It would probably bring you way more additional information on a very high resolution image like SPOT</div><div><br></div><div>I used the GRASS texture tool. But there are so many outputs and parameters that you can set, that you might quickly become overwhelmed with too many data outputs.</div><div></div><div></div><div>To help with that, I ran a PCA transformation on the Sentinel-2 spectral bands, then only ran texture on the PCA band that was most obviously discerning the features I was interested in.</div><div></div><div><br></div><div>You might also have to reduce the radiometric resolution of the data on which you want to calculate texture (e.g from the original 16 or 32 bits to 8 bits) otherwise your RAM is likely to explode when GRASS calculates the grey level co-occurrence matrix.</div><div>Good luck</div><div><br></div></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Tue, 4 Mar 2025 at 22:06, celati Laurent via QGIS-User <<a href="mailto:qgis-user@lists.osgeo.org">qgis-user@lists.osgeo.org</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 dir="ltr">
<p>Hello.<br>
My goal is to generate a relevant segmentation that would delimit the
main physiopnomic units (homogenous areas). Up to now, I have done
several tests with qgis and orfeotoolbox 9 with the OTB Generic Region
merging module : <a href="https://www.orfeo-toolbox.org/CookBook-7.0/Applications/app_GenericRegionMerging.html" rel="noopener nofollow ugc" target="_blank">GenericRegionMerging — Orfeo ToolBox 7.0.0 documentation</a> with those folowing settings</p>
<ul><li>input image : spot 6/7 satelite image (band blue, green, red, near infrared)<br>
or Aerial french mapping agency images (50 cms bd ortho with green, red and near infrared).<br>
*Homogenity criterion to use : Baatz & Schape</li><li>Threshold for the criterion : 500</li><li>Number of iterations`: 0</li><li>Weight for the spectral homogeneity : 0.1</li><li>Weight for the spatial homogeneity : 0.1</li></ul>
<p>The result is rather interesting for certain areas, in particular
crops areas, without too much vegetation. on the other hand, the method
does not seems optimal, in particular for forest areas.<br>
I’m taking the liberty to paste some screenshots :<br>
the first SS showing interesting result on crop areas :</p>
<br><div><img src="cid:ii_m7uka7lh0" alt="4d3f841e567bd5ac5ce37035342c4e71e78d16c6.jpeg" width="257" height="194" style="margin-right: 0px;"></div><div>
A second SS showing the non relevant result on forest areas : <br></div><div><img src="cid:ii_m7ukaojr1" alt="9b64943de826eddd230762b3d2a5eb358cc423ec.jpeg" width="260" height="143" style="margin-right: 0px;"></div><div>
Perhaps for these forest areas, the color/spectral criterion is not
relevant. It would be better to generate / integrate texture
information? As far as i understood, this GRM OTB module is based only
on spectral/colour criterion but not take into consideration texture
information.<br>
Are there other orfeotoolbox segmentation module that takes into account
not only the color criterion (spectral) but also texture information?<br>
If this is not the case, should i create some kind of new raster (add a
band to my existing color infrared raster) dedicated to texture and/or
ndvi information?<br>
Thanks so much for your guidances.
<br><br></div><br><br></div>
_______________________________________________<br>
QGIS-User mailing list<br>
<a href="mailto:QGIS-User@lists.osgeo.org" target="_blank">QGIS-User@lists.osgeo.org</a><br>
List info: <a href="https://lists.osgeo.org/mailman/listinfo/qgis-user" rel="noreferrer" target="_blank">https://lists.osgeo.org/mailman/listinfo/qgis-user</a><br>
Unsubscribe: <a href="https://lists.osgeo.org/mailman/listinfo/qgis-user" rel="noreferrer" target="_blank">https://lists.osgeo.org/mailman/listinfo/qgis-user</a><br>
</blockquote></div>