Tool Seeded Region Growing
The tool allows one to apply a seeded region growing algorithm to a stack of input features and thus to segmentize the data for object extraction. The required seed points can be created with the 'Seed Generation' tool, for example. The derived segments can be used, for example, for object based classification.
References
- Adams, R. & Bischof, L. (1994): Seeded Region Growing. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.16, No.6, p.641-647. online.
- Bechtel, B., Ringeler, A. & Boehner, J. (2008): Segmentation for Object Extraction of Trees using MATLAB and SAGA. In: Boehner, J., Blaschke, T., Montanarella, L. [Eds.]: SAGA - Seconds Out. Hamburger Beitraege zur Physischen Geographie und Landschaftsoekologie, 19:59-70. online.
- Author: B. Bechtel, O. Conrad (c) 2008
- Menu: Imagery|Segmentation
Parameters
| Name | Type | Identifier | Description | Constraints |
Input | Seeds | Grid, input | SEEDS | - | - |
Features | Grid list, input | FEATURES | - | - |
Output | Segments | Grid, output | SEGMENTS | - | - |
Similarity | Grid, output | SIMILARITY | - | - |
Seeds | Table, output | TABLE | - | - |
Options | Grid System | Grid system | PARAMETERS_GRID_SYSTEM | - | - |
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 |
Neighbourhood | Choice | NEIGHBOUR | - | Available Choices: [0] 4 (von Neumann) [1] 8 (Moore) Default: 0 |
Method | Choice | METHOD | - | Available Choices: [0] feature space and position [1] feature space Default: 0 |
Variance in Feature Space | Floating point | SIG_1 | - | Minimum: 0.000000 Default: 1.000000 |
Variance in Position Space | Floating point | SIG_2 | - | Minimum: 0.000000 Default: 1.000000 |
Similarity Threshold | Floating point | THRESHOLD | - | Minimum: 0.000000 Default: 0.000000 |
Refresh | Boolean | REFRESH | - | Default: 0 |
Leaf Size (for Speed Optimisation) | Integer | LEAFSIZE | - | Minimum: 2 Default: 256 |
Command-line
Usage: saga_cmd imagery_segmentation 3 [-SEEDS <str>] [-FEATURES <str>] [-SEGMENTS <str>] [-SIMILARITY <str>] [-TABLE <str>] [-NORMALIZE <str>] [-NEIGHBOUR <str>] [-METHOD <str>] [-SIG_1 <double>] [-SIG_2 <double>] [-THRESHOLD <double>] [-REFRESH <str>] [-LEAFSIZE <num>]
-SEEDS:<str> Seeds
Grid, input
-FEATURES:<str> Features
Grid list, input
-SEGMENTS:<str> Segments
Grid, output
-SIMILARITY:<str> Similarity
Grid, output
-TABLE:<str> Seeds
Table, output
-NORMALIZE:<str> Normalize Features
Boolean
Default: 0
-NEIGHBOUR:<str> Neighbourhood
Choice
Available Choices:
[0] 4 (von Neumann)
[1] 8 (Moore)
Default: 0
-METHOD:<str> Method
Choice
Available Choices:
[0] feature space and position
[1] feature space
Default: 0
-SIG_1:<double> Variance in Feature Space
Floating point
Minimum: 0.000000
Default: 1.000000
-SIG_2:<double> Variance in Position Space
Floating point
Minimum: 0.000000
Default: 1.000000
-THRESHOLD:<double> Similarity Threshold
Floating point
Minimum: 0.000000
Default: 0.000000
-REFRESH:<str> Refresh
Boolean
Default: 0
-LEAFSIZE:<num> Leaf Size (for Speed Optimisation)
Integer
Minimum: 2
Default: 256