Tool Seed Generation
The tool allows one to create seed points from a stack of input features. Such seed points can be used, for example, as input in the 'Seeded Region Growing' tool.
- Author: O.Conrad (c) 2010
- Menu: Imagery|Segmentation
Parameters
| Name | Type | Identifier | Description | Constraints |
Input | Features | Grid list, input | FEATURES | - | - |
Output | Variance | Grid, output | VARIANCE | - | - |
Seeds Grid (*) | Grid, output, optional | SEED_GRID | - | - |
Seed Points (*) | Shapes, output, optional | SEED_POINTS | - | - |
Options | Grid System | Grid system | PARAMETERS_GRID_SYSTEM | - | - |
Seed Type | Choice | SEED_TYPE | - | Available Choices: [0] minima of variance [1] maxima of variance Default: 0 |
Method | Choice | METHOD | - | Available Choices: [0] band width smoothing [1] band width search Default: 0 |
Bandwidth (Cells) | Floating point | BAND_WIDTH | - | Minimum: 1.000000 Default: 10.000000 |
Normalize Features | Boolean | NORMALIZE | Standardize the input features, i.e. rescale the input data (features) such that the mean equals 0 and the standard deviation equals 1. This is helpful when the input features have different scales, units or outliers. | Default: 0 |
Weighting Function | Choice | DW_WEIGHTING | - | Available Choices: [0] no distance weighting [1] inverse distance to a power [2] exponential [3] gaussian Default: 0 |
Power | Floating point | DW_IDW_POWER | - | Minimum: 0.000000 Default: 2.000000 |
Bandwidth | Floating point | DW_BANDWIDTH | Bandwidth for exponential and Gaussian weighting | Minimum: 0.000000 Default: 1.000000 |
(*) optional |
Command-line
Usage: saga_cmd imagery_segmentation 2 [-FEATURES <str>] [-VARIANCE <str>] [-SEED_GRID <str>] [-SEED_POINTS <str>] [-SEED_TYPE <str>] [-METHOD <str>] [-BAND_WIDTH <double>] [-NORMALIZE <str>] [-DW_WEIGHTING <str>] [-DW_IDW_POWER <double>] [-DW_BANDWIDTH <double>]
-FEATURES:<str> Features
Grid list, input
-VARIANCE:<str> Variance
Grid, output
-SEED_GRID:<str> Seeds Grid
Grid, output, optional
-SEED_POINTS:<str> Seed Points
Shapes, output, optional
-SEED_TYPE:<str> Seed Type
Choice
Available Choices:
[0] minima of variance
[1] maxima of variance
Default: 0
-METHOD:<str> Method
Choice
Available Choices:
[0] band width smoothing
[1] band width search
Default: 0
-BAND_WIDTH:<double> Bandwidth (Cells)
Floating point
Minimum: 1.000000
Default: 10.000000
-NORMALIZE:<str> Normalize Features
Boolean
Default: 0
-DW_WEIGHTING:<str> Weighting Function
Choice
Available Choices:
[0] no distance weighting
[1] inverse distance to a power
[2] exponential
[3] gaussian
Default: 0
-DW_IDW_POWER:<double> Power
Floating point
Minimum: 0.000000
Default: 2.000000
-DW_BANDWIDTH:<double> Bandwidth
Floating point
Minimum: 0.000000
Default: 1.000000