1i.gensig(1) GRASS GIS User's Manual i.gensig(1)
2
6 i.gensig - Generates statistics for i.maxlik from raster map.
7
9 imagery, classification, supervised classification, Maximum Likelihood
10 Classification, MLC, signatures
11
13 i.gensig
14 i.gensig --help
15 i.gensig trainingmap=name group=name subgroup=name signaturefile=name
16 [--overwrite] [--help] [--verbose] [--quiet] [--ui]
17 Flags:
19 --overwrite
20 Allow output files to overwrite existing files
21 --help
23 Print usage summary
24 --verbose
26 Verbose module output
27 --quiet
29 Quiet module output
30 --ui
32 Force launching GUI dialog
33 Parameters:
35 trainingmap=name [required]
36 Ground truth training map
37 group=name [required]
39 Name of input imagery group
40 subgroup=name [required]
42 Name of input imagery subgroup
43 signaturefile=name [required]
45 Name for output file containing result signatures
46
48 i.gensig is a non-interactive method for generating input into i.max‐
49 lik. It can be used as the first pass in the GRASS two-pass classifi‐
50 cation process (instead of i.cluster or g.gui.iclass). It reads a
51 raster map layer, called the training map, which has some of the pixels
52 or regions already classified. i.gensig will then extract spectral
53 signatures from an image based on the classification of the pixels in
54 the training map and make these signatures available to i.maxlik.
55 The user would then execute the GRASS program i.maxlik to actually cre‐
57 ate the final classified map.
58 All raster maps used to generate signature file can have semantic label
60 set. Use r.support to set semantic labels of each member of the imagery
61 group. Signatures generated for one scene are suitable for classifica‐
62 tion of other scenes as long as they consist of same raster bands (se‐
63 mantic labels match).
64
66 Parameters
67 trainingmap=name
68 ground truth training map
69 This map must be prepared by the user in advance using vector or raster
71 digitizer. Of course other methods could be devised by the user for
72 creating this training map - i.gensig makes no assumption about the
73 origin of this map layer. It simply creates signatures for the classes
74 defined in the training map for the image to be classified (the image
75 is specified in other options - see below). The wxGUI vector digitizer
76 can be used for interactively creating the training map.
77 group=name
79 imagery group
80 This is the name of the group that contains the band files which com‐
82 prise the image to be analyzed. The i.group command is used to con‐
83 struct groups of raster layers which comprise an image.
84 subgroup=name
86 subgroup containing image files
87 This names the subgroup within the group that selects a subset of the
89 bands to be analyzed. The i.group command is also used to prepare this
90 subgroup. The subgroup mechanism allows the user to select a subset of
91 all the band files that form an image.
92 signaturefile=name
94 resultant signature file
95 This is the resultant signature file (containing the means and covari‐
97 ance matrices) for each class in the training map that is associated
98 with the band files in the subgroup select (see above). Resultant sin‐
99 gature file can be used with any other imagery group as long as seman‐
100 tic labels match.
101
103 The structure of the SIG files generated by i.gensig is as follows
104 (ASCII file, used internally by i.maxlik):
105 Note: the line numbers are not present in the file but have been added
106 here for explanation only:
107 SIG file "lsat7_2000_gensig":
109 1 1
110 2 #
111 3 Semantic_label1
112 4 #water
113 5 4186
114 6 67.9508 48.7346 37.8915 15.3129 13.8473 12.0855
115 7 1.74334
116 8 0.439504 2.07267
117 9 0.662523 1.63501 4.21189
118 10 0.530339 2.40757 5.52857 22.433
119 11 0.561184 2.30762 5.18846 20.5364 20.4926
120 12 0.393218 1.2184 2.63628 9.61528 9.36025 5.85314
121 • Line 1: version number (currently always 1)
123 • Line 2: text label
125 • Line 3: Space separated list of semantic labels
127 • Line 4: text label of class
129 • Line 5: number of points in class
131 • Line 6: mean values per band of the class
133 • Line 7-12: (semi)-matrix of band-band covariance
135
137 r.support, g.gui.iclass, i.group, i.cca, i.maxlik, i.smap, r.info,
138 r.univar, wxGUI vector digitizer
139
141 Michael Shapiro, U.S.Army Construction Engineering Research Laboratory
142 Semantic label support: Maris Nartiss, University of Latvia
143
145 Available at: i.gensig source code (history)
146 Accessed: Mon Jun 20 16:47:29 2022
148 Main index | Imagery index | Topics index | Keywords index | Graphical
150 index | Full index
151 © 2003-2022 GRASS Development Team, GRASS GIS 8.2.0 Reference Manual
153GRASS 8.2.0 i.gensig(1)