NAME

i.segment mean shift algorithm - Identifies segments (objects) from imagery data using mean shift algorithm.

KEYWORDS

imagery, segmentation,

SYNOPSIS

i.segment

i.segment [-dwap] group=name output=name [band_suffix=name] threshold=value [radius=value] [hr=value] [method=string] [similarity=string] [minsize=value] [memory=value] [iterations=value] [seeds=name] [bounds=name] [goodness=name] [--overwrite] [--help] [--verbose] [--quiet] [--ui]

Flags:

-d
Use 8 neighbors (3x3 neighborhood) instead of the default 4 neighbors for each pixel

-w
Weighted input, do not perform the default scaling of input raster maps

-a
Use adaptive bandwidth for mean shift
Range (spectral) bandwidth is adapted for each moving window -p
Use progressive bandwidth for mean shift
Spatial bandwidth is increased, range (spectral) bandwidth is decreased in each iteration

--o
Allow output files to overwrite existing files

--h
Print usage summary

--v
Verbose module output

--q
Quiet module output

--qq
Super quiet module output

--ui
Force launching GUI dialog

PARAMETERS

group=name [required]

Name of input imagery or imagery group

output=name [required]

Name of output segmentation map

threshold=value [required]

Difference threshold between 0 and 1 Threshold = 0 merges only identical segments; threshold = 1 merges all

band_suffix=name

Suffix for output bands with shifted mean value

radius=value

spatial bandwidth in number of cells

hr=value

range bandwidth in number of cells

method=string

Segmentation method Options: region_growing, mean_shift, watershed

similarity=string

Similarity calculation method Options: euclidean, manhattan Default: euclidean

minsize=value

Minimum number of cells in a segment The final step will merge small segments with their best neighbor Options: 1-100000 Default: 1

memory=value

Memory in MB Default: 300

iterations=value

Maximum number of iterations during the mean shift process

seeds=name

Name for input raster map with starting seeds

bounds=name

Name of input bounding/constraining raster map

goodness=name

Name for output goodness of fit estimate map

--overwrite

Boolean if overtie the existing raster

--ui

run with the user interface mode

--help

--verbose

--quiet

DESCRIPTION