i.gensig - GRASS GIS manual

Note: This document is for an older version of GRASS GIS that is outdated. You should upgrade, and read the current manual page.

NAME

i.gensig - Generates statistics for i.maxlik from raster map.

KEYWORDS

imagery, classification, supervised classification, Maximum Likelihood Classification, MLC, signatures

SYNOPSIS

i.gensig

i.gensig --help

i.gensig trainingmap=name group=name subgroup=name signaturefile=name [--overwrite] [--help] [--verbose] [--quiet] [--ui]

Flags:

--overwrite: Allow output files to overwrite existing files
--help: Print usage summary
--verbose: Verbose module output
--quiet: Quiet module output
--ui: Force launching GUI dialog

Parameters:

trainingmap=name [required]: Ground truth training map
group=name [required]: Name of input imagery group
subgroup=name [required]: Name of input imagery subgroup
signaturefile=name [required]: Name for output file containing result signatures

DESCRIPTION
OPTIONS
- Parameters
NOTES
SEE ALSO
AUTHORS

DESCRIPTION

i.gensig is a non-interactive method for generating input into i.maxlik. It can be used as the first pass in the GRASS two-pass classification process (instead of i.cluster or g.gui.iclass). It reads a raster map layer, called the training map, which has some of the pixels or regions already classified. i.gensig will then extract spectral signatures from an image based on the classification of the pixels in the training map and make these signatures available to i.maxlik.

The user would then execute the GRASS program i.maxlik to actually create the final classified map.

All raster maps used to generate signature file can have semantic label set. Use r.support to set semantic labels of each member of the imagery group. Signatures generated for one scene are suitable for classification of other scenes as long as they consist of same raster bands (semantic labels match).

OPTIONS

Parameters

trainingmap=name

ground truth training map

This map must be prepared by the user in advance using vector or raster digitizer. Of course other methods could be devised by the user for creating this training map - i.gensig makes no assumption about the origin of this map layer. It simply creates signatures for the classes defined in the training map for the image to be classified (the image is specified in other options - see below). The wxGUI vector digitizer can be used for interactively creating the training map.

group=name

imagery group

This is the name of the group that contains the band files which comprise the image to be analyzed. The i.group command is used to construct groups of raster layers which comprise an image.

subgroup=name

subgroup containing image files

This names the subgroup within the group that selects a subset of the bands to be analyzed. The i.group command is also used to prepare this subgroup. The subgroup mechanism allows the user to select a subset of all the band files that form an image.

signaturefile=name

resultant signature file

This is the resultant signature file (containing the means and covariance matrices) for each class in the training map that is associated with the band files in the subgroup select (see above). Resultant singature file can be used with any other imagery group as long as semantic labels match.

NOTES

The structure of the SIG files generated by i.gensig is as follows (ASCII file, used internally by i.maxlik):
Note: the line numbers are not present in the file but have been added here for explanation only:

SIG file "lsat7_2000_gensig":

 1 1
 2 #
 3 Semantic_label1
 4 #water
 5 4186
 6 67.9508 48.7346 37.8915 15.3129 13.8473 12.0855 
 7 1.74334 
 8 0.439504 2.07267 
 9 0.662523 1.63501 4.21189 
10 0.530339 2.40757 5.52857 22.433 
11 0.561184 2.30762 5.18846 20.5364 20.4926 
12 0.393218 1.2184 2.63628 9.61528 9.36025 5.85314

Line 1: version number (currently always 1)
Line 2: text label
Line 3: Space separated list of semantic labels
Line 4: text label of class
Line 5: number of points in class
Line 6: mean values per band of the class
Line 7-12: (semi)-matrix of band-band covariance

AUTHORS

Michael Shapiro, U.S.Army Construction Engineering Research Laboratory
Semantic label support: Maris Nartiss, University of Latvia

SOURCE CODE

Available at: i.gensig source code (history)

Latest change: Thu Feb 3 11:10:06 2022 in commit: 73413160a81ed43e7a5ca0dc16f0b56e450e9fef