<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html; charset=windows-1255"
http-equiv="Content-Type">
<title></title>
</head>
<body text="#000000" bgcolor="#ffffff">
On 04/01/2010 02:52 PM, Nathaniel Iwuchukwu wrote:
<blockquote
cite="mid:x2n2336bcfa1004010452k33bff764nba216b947b5cbf44@mail.gmail.com"
type="cite">
<div>i created 11 polygons from different portions of the road.</div>
</blockquote>
So if I understand correctly, the procedure is working, but you're not
getting the results you'd expect?<br>
Maybe you could supply to the grass-users list some URL's of images of
what the satellite rasters look like, with your training polygons, and
the resulting roads. Then perhaps someone will be able to suggest how
to get more complete results. <br>
<blockquote
cite="mid:x2n2336bcfa1004010452k33bff764nba216b947b5cbf44@mail.gmail.com"
type="cite">
<div><br>
<br>
</div>
<div class="gmail_quote">2010/4/1 Micha Silver <span dir="ltr"><<a
moz-do-not-send="true" href="mailto:micha@arava.co.il">micha@arava.co.il</a>></span><br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote">
<div bgcolor="#ffffff" text="#000000">
<div class="im">On 04/01/2010 01:11 AM, Nathaniel Iwuchukwu wrote: </div>
<blockquote type="cite">
<div>Thanks Micha,</div>
<div class="im">
<div>I ran r.thin and got just one line. is there a way i can
improve it?<br>
<br>
</div>
</div>
</blockquote>
<div class="im">Good, so we're making progress...<br>
How many polygon areas did you create in the training map? Does it
cover various portions of the roads?<br>
</div>
<blockquote type="cite">
<div class="gmail_quote">On Wed, Mar 31, 2010 at 1:54 PM, Micha
Silver <span dir="ltr"><<a moz-do-not-send="true"
href="mailto:micha@arava.co.il" target="_blank">micha@arava.co.il</a>></span>
wrote:
<div>
<div class="h5"><br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote">
<div>Nathaniel Iwuchukwu wrote:<br>
<br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote">Also, when i convert from vector to raster, i
don't see anything on the new raster map. its all blank. what should i
do. thanks<br>
</blockquote>
</div>
I guess that would explain why you're getting "Training map has no
classes".<br>
Can you display the vector which covers sections of the road? Do you
see filled polygons?<br>
If not maybe you made boundaries with no centroids? In GRASS, area
features must be composed of both a boundary *and* a centroid. In the
digitizer there's a special button for adding a centroid. You need one
inside each polygon boundary.<br>
<br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote">
<div><br>
On Wed, Mar 31, 2010 at 11:20 AM, Nathaniel Iwuchukwu <<a
moz-do-not-send="true" href="mailto:ikechinedu@gmail.com"
target="_blank">ikechinedu@gmail.com</a> <mailto:<a
moz-do-not-send="true" href="mailto:ikechinedu@gmail.com"
target="_blank">ikechinedu@gmail.com</a>>> wrote:<br>
<br>
Thanks Micha,<br>
I will definately post it once i scale through it.<br>
i am getting an error when i run the i.gensigset on the training
data.<br>
this is what i typed and the result:<br>
GRASS 6.4.0RC5 (sis):~/Desktop > i.gensigset trainingmap=traingis<br>
group=sislabgp subgroup=sislabsub signaturefile=sislab.sig<br>
Finding training classes...<br>
100%<br>
ERROR: Training map has no classes<br>
do you have any clue why i don't have a class?<br>
Thanks Man<br>
</div>
2010/3/31 Micha Silver <<a moz-do-not-send="true"
href="mailto:micha@arava.co.il" target="_blank">micha@arava.co.il</a>
<mailto:<a moz-do-not-send="true" href="mailto:micha@arava.co.il"
target="_blank">micha@arava.co.il</a>>>
<div><br>
<br>
On 03/31/2010 01:19 AM, Nathaniel Iwuchukwu wrote:<br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote"> Thanks Micha,<br>
this looks good but am still working on it. would you know<br>
the RGB for a road? from the link you<br>
</blockquote>
No, I can't tell what the RGB values for a road would be, and<br>
it will change from image to image, and from road to road.<br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote"> sent me, i will need it to capture the
pixel values of road<br>
polygons that i am digitizing.<br>
</blockquote>
You *don't* need to find the actual pixel values for the road<br>
polygons. You just digitize strips that cover the road, and<br>
feed these areas (after converting to a raster) as the<br>
training map. The gensigset module creates the collection of<br>
pixels values that match "roads"<br>
<br>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote"> thanks Micha. you really gave me a lead.<br>
</blockquote>
Good. Post back to the list when you get it worked out.<br>
<br>
<br>
</div>
<blockquote
style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;"
class="gmail_quote">
<div> Nathaniel<br>
<br>
On Tue, Mar 30, 2010 at 4:26 PM, Micha Silver<br>
</div>
<div>
<div> <<a moz-do-not-send="true"
href="mailto:micha@arava.co.il" target="_blank">micha@arava.co.il</a>
<mailto:<a moz-do-not-send="true" href="mailto:micha@arava.co.il"
target="_blank">micha@arava.co.il</a>>> wrote:<br>
<br>
Nathaniel Iwuchukwu wrote:<br>
<br>
sorry my typo. i mean classification.<br>
<br>
I didn't intend to insult. Sometimes typos come out<br>
funny, and I can't resist pointing it out...<br>
<br>
but am looking for procedure on road extraction from<br>
satellite imagery with high resolution<br>
<br>
OK, you'll probably want to use "supervised"<br>
classification. This means giving the classification<br>
algorithm a "training" layer. So the process involves<br>
1- First create a vector layer using the grass digitizer<br>
with small polygons covering some sections of the roads<br>
in the satellite image. Convert the vector to a raster<br>
(v.to.rast). This will be the training map.<br>
2- Now group the satellite bands into an imagery group<br>
(i.group)<br>
3- Run i.gensigset with the training raster and the<br>
imagery group.<br>
4- Now use i.smap with the signature file and imagery<br>
group as input, and a classification map as output.<br>
5- If the results look good, run r.thin on this raster,<br>
and then r.to.vect to see what you get.<br>
<br>
Here's a more detailed explanation that you might find<br>
helpful:<br>
<a moz-do-not-send="true"
href="http://www.surfaces.co.il/?p=3" target="_blank">http://www.surfaces.co.il/?p=3</a><br>
<br>
Regards,<br>
Micha<br>
<br>
<br>
</div>
</div>
</blockquote>
<div>
<div><br>
-- Micha Silver<br>
<a moz-do-not-send="true" href="http://www.surfaces.co.il/"
target="_blank">http://www.surfaces.co.il/</a><br>
Arava Development Co. +972-52-3665918<br>
<br>
<br>
<br>
<br>
</div>
</div>
<div>This mail was received via Mail-SeCure System.<br>
</div>
</blockquote>
<br>
<br>
-- <br>
<font color="#888888">Micha Silver</font>
<div><br>
Arava Development Co. +972-52-3665918<br>
</div>
<div>
<div><a moz-do-not-send="true" href="http://www.surfaces.co.il/"
target="_blank">http://www.surfaces.co.il</a><br>
<br>
<br>
</div>
</div>
</blockquote>
</div>
</div>
</div>
<div>
<div class="h5"><br>
<br>
This mail was received via Mail-SeCure System.<br>
</div>
</div>
</blockquote>
<div>
<div class="h5"><br>
<br>
<pre cols="72">--
Micha Silver
<a moz-do-not-send="true" href="http://www.surfaces.co.il/"
target="_blank">http://www.surfaces.co.il/</a>
Arava Development Co. +972-52-3665918</pre>
</div>
</div>
</div>
</blockquote>
</div>
<br>
<br>
This mail was received via Mail-SeCure System.<br>
</blockquote>
<br>
<br>
<pre class="moz-signature" cols="72">--
Micha Silver
<a class="moz-txt-link-freetext" href="http://www.surfaces.co.il/">http://www.surfaces.co.il/</a>
Arava Development Co. +972-52-3665918</pre>
</body>
</html>