<div>Dear Wout,</div>
<div> </div>
<div>Following Jonathan´s comments about window size selecion, give a look at:</div>
<div><br>RIBEIRO, M. C. ; ALVES, D. S. ; YANASSE, C. C. F. ; SOARES, J. V. ; II, F. M. . Window size selection for SAR classification using texture measures: a case study of a Brazilian Amazon test site. In: Segunda jornada latino-americana de sensoriamento remoto por radar: técnicas de processamento de imagens, 1998, Santos, SP. Segunda jornada latino-americana de sensoriamento remoto por radar: técnicas de processamento de imagens, 1998</div>
<div> </div>
<div><a href="http://marte.dpi.inpe.br/col/sid.inpe.br/deise/1999/02.11.16.14/doc/10_213o.pdf">http://marte.dpi.inpe.br/col/sid.inpe.br/deise/1999/02.11.16.14/doc/10_213o.pdf</a></div>
<div> </div>
<div>Best wishes,</div>
<div> </div>
<div>miltinho<br><br> </div>
<div><span class="gmail_quote">2008/8/22, Jonathan Greenberg <<a href="mailto:greenberg@ucdavis.edu">greenberg@ucdavis.edu</a>>:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Wout:<br><br> This is more of a general response, rather than a "how to" for GRASS. At 1m, you are absolutely going to need to include some level of spatial processing (texture being the "brute force" way of getting at these sorts of things). At that resolution, trees become multi-pixel objects, and there will be more spectral variation within a tree crown than between any two trees. Which textures to try are an issue you will need to resolve by experimentation -- variance is often an important factor, average less so. The window size choice is extremely important, because each window size is picking up different pieces of information. For instance, for large trees at 1m, a 3x3 window is going to be picking up within-crown variation, so you will get high values near the sunlit-to-shadow transition, and near the crown edges, but low variation within the shadow or within the sunlit portions of the tree. Your window should be larger than a tree crown if you expect to get fairly similar values within the tree crown (which is critical if you want to approach this in a pixel based approach). I don't recommend pixel-based approaches for macro-pixel objects, however.<br>
<br> When working with "hyperspatial" remote sensing data, keep in mind you are classifying "trees" as unique landscape objects (polygons, really), not the less well defined "forest" -- as such, you should try to employ object-based approaches. You can google scholar "tree crown remote sensing" to get some ideas on how people approach this problem. Keep an eye out for papers by Lefsky, Pouliot, Popescu, Wulder, and Leckie, amongst others. If you want to understand how to scale from tree crown objects to a "forest" I'll tout one of my papers:<br>
<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://casil.ucdavis.edu/docman/view.php/52/141/greenbergetal2006b.pdf" target="_blank">http://casil.ucdavis.edu/docman/view.php/52/141/greenbergetal2006b.pdf</a><br>
<br> It would be cool to implement some of these algorithms in GRASS, but to my knowledge there is no package (you'd have to write one) -- in fact, very few remote sensing packages have even the beginnings of these capabilities, although some of the authors I mention above may be willing to share their code. <br>
--j
<div><span class="e" id="q_11beb92e36998167_1"><br><br>Wout Bijkerk wrote:<br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Hello everybody,<br><br>I am trying to perform a supervised classification of false color<br>images. The resolution of the bands (IR,R,G) is 1 meter. Additionally I<br>
can use a DEM as input ( hor. res. = 5m), but apparently null-values<br>within the training areas are causing some problems (see<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://lists.osgeo.org/pipermail/grass-user/2008-June/045261.html" target="_blank">http://lists.osgeo.org/pipermail/grass-user/2008-June/045261.html</a>) so I<br>
am not using the DEM for the moment. I intend to use the combined<br>radiometric and geometric modules i.gensigset and i.smap.<br><br>Looking at the images, I wonder if including textural features within<br>the images would be usefull: a forest canopy has a far coarser texture<br>
than a grassland. Also in the Grassbook this is mentioned, and for the<br>supervised classification of saltmarshes in Germany, textural features<br>are also used (see i.e.<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://www.nature-consult.de/images/downl/Agit_2008_nature-consult.pdf" target="_blank">http://www.nature-consult.de/images/downl/Agit_2008_nature-consult.pdf</a>,<br>
but in German), but this is not further explained.<br><br>This brings me to the following questions:<br><br>1) Is it usefull to make a raster with textural image features as an<br>extra input for i.gensigset / i.smap? The i.gensigset / i.smap procedure<br>
is partly based on geometry and therefor on texture as well so what does<br>a texturemap add?<br>2) if it is usefull, which textural feature is then aproppriate? I have<br>been experimenting and until now simply variance seems to make the<br>
difference between forest and shrubland compared to grassland, and<br>reed-vegetation. This was using a windowsize of 5, meaning 5x5 m.<br><br>Did anyone have any experience with this?<br><br>Regards,<br><br>Wout<br><br> _______________________________________________<br>
grass-user mailing list<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:grass-user@lists.osgeo.org" target="_blank">grass-user@lists.osgeo.org</a><br><a onclick="return top.js.OpenExtLink(window,event,this)" href="http://lists.osgeo.org/mailman/listinfo/grass-user" target="_blank">http://lists.osgeo.org/mailman/listinfo/grass-user</a><br>
<br> <br></blockquote><br></span></div>-- <br>Jonathan A. Greenberg, PhD<br>Postdoctoral Scholar<br>Center for Spatial Technologies and Remote Sensing (CSTARS)<br>University of California, Davis<br>One Shields Avenue<br>The Barn, Room 250N<br>
Davis, CA 95616<br>Cell: 415-794-5043<br>AIM: jgrn307, MSN: <a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:jgrn307@hotmail.com" target="_blank">jgrn307@hotmail.com</a>, Gchat: jgrn307
<div><span class="e" id="q_11beb92e36998167_3"><br><br>_______________________________________________<br>grass-user mailing list<br><a onclick="return top.js.OpenExtLink(window,event,this)" href="mailto:grass-user@lists.osgeo.org" target="_blank">grass-user@lists.osgeo.org</a><br>
<a onclick="return top.js.OpenExtLink(window,event,this)" href="http://lists.osgeo.org/mailman/listinfo/grass-user" target="_blank">http://lists.osgeo.org/mailman/listinfo/grass-user</a><br></span></div></blockquote></div>
<br>