Nathaniel Iwuchukwu wrote:

I figured it out.
here are my new output. though the lines are scattered. can it be improved?
Again, Nathaniel, keep the discussion on the list, both to get more responses, and for future generations. The next step you might try is using the v.clean command on this vector to remove very small lines. It has a tool, rmdangle to get rid of all the small X's around the actual roads. You will have to experiment with the "thresh" parameter to get it right.

Regards,
Micha

On Fri, Apr 2, 2010 at 5:41 AM, Nathaniel Iwuchukwu <[email protected] <mailto:[email protected]>> wrote:

    Thanks Micha,
    I was thinking of running the r.mapcalc command but not sure of
    the exact argument to use.
    is there a command i can run to show me the values of the colors
    on the map?
    Thanks
    Nathaniel

    On Fri, Apr 2, 2010 at 8:27 AM, Micha Silver <[email protected]
    <mailto:[email protected]>> wrote:

        Nathaniel Iwuchukwu wrote:

            here are the image results of my works. am trying to
            upload it on my page

        If you do upload the images, post also to the list.

        It looks like all the areas that are *not* roads are also
        being classified. Everywhere that appears purple in you
        classification image needs to be set to null. You do this with:
        r.null <classified_raster> setnull=<the value which displays
        purple>

        You want to be left with a raster with values *only* where
        there are roads. Everything else should be null. Then go ahead
        and run:
        r.thin and r.to.vect <classified_raster_thin> feature=line
        out=roads

        Cheers,
        Micha


            2010/4/1 Micha Silver <[email protected]
            <mailto:[email protected]> <mailto:[email protected]
            <mailto:[email protected]>>>


               On 04/01/2010 02:52 PM, Nathaniel Iwuchukwu wrote:

                   i created 11 polygons from different portions of
                the road.

               So if I understand correctly, the procedure is working,
            but you're
               not getting the results you'd expect?

               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.








This mail was received via Mail-SeCure System.

------------------------------------------------------------------------


------------------------------------------------------------------------



--
Micha Silver
Arava Development Co. +972-52-3665918
http://www.surfaces.co.il


_______________________________________________
grass-user mailing list
[email protected]
http://lists.osgeo.org/mailman/listinfo/grass-user

Reply via email to