Dear Users,
I'm trying to find out an algorithm capable to slice urban areas in
different density sets using Tm data. Has anyone any idea about that?
Thanks
Piero
Piero Boccardo - Italy (DORICE@polito.it) writes to
grassu-list@moon.cecer.army.mil on 8 March 1995:
I'm trying to find out an algorithm capable to slice urban areas in
different density sets using Tm data. Has anyone any idea about that?
I'd suggest looking at i.gensigset and i.smap (Sequential MAP, see
appended refs).
I assume that you're talking about population densities - if
that's the case, I would be inclined to take a more naive approach
of calculating a texture map (one of Haralick's features; see i.texture
in GRASS) of just one band and seeing what kind of correlations this
gives me, but then again I may be doing things the hard way.
The kind folks on the IMAGRS list may be able to provide an
answer or at least some leads to previous work.
--
James Darrell McCauley, PhD http://soils.ecn.purdue.edu/~mccauley/
Dept of Agricultural Engineering mccauley@ecn.purdue.edu
Purdue University new-> tel: 317.494.1198 fax: 317.496.1115
@Article{ bouman94,
author = "Charles Bouman and Michael Shapiro",
title = "A Multiscale Random Field Model for {B}ayesian Image
Segmentation",
journal = "IEEE Transactions on Image Processing",
year = 1994,
volume = 3,
number = 2,
pages = "162--177",
month = mar
}
@InProceedings{ bouman92,
author = "Charles Bouman and Michael Shapiro",
title = "Multispectral Image Segmentation using a Multiscale
Image Model",
pages = "III-565--III-568",
booktitle = "Proc. of IEEE Int'l Conf. on Acoust., Speech and Sig. Proc.",
year = "1992",
organization = "IEEE",
address = "San Francisco, " # CA,
month = "March 23--26"
}