Raster_UnsupervisedClassificationService
This service serves to reclassify multispectral satellite data using unsupervised classification method based on the maximum-likelihood classifier (MLC) algorithm.
Operation:
unsupervised - Unsupervised reclassification is the automated assignment of raster pixels to different spectral classes. The assignment is based only on the image statistics. The algorithm is called the maximum-likelihood classifier (MLC).
The unsupervised reclassification starts with collecting the image channels of interest (i.e. for optical data usually all reflective channels without thermal channel) into an image group. It is important to set the initial number of classes used for the first iteration ("number of initial classes"); for other parameters, you may use default values for the first try.[Markus Neteler and Helena Mitasova, 2004].
Request Parameters:
- sourceURLArray
- URL Array of a group of imagery files to be classified
- Default format: GeoTIFF
- classes
- Initial number of classes
- Parameter format: integer
- Options: 1-255
- iterations
- Maximum number of iterations
- Parameter format: integer
- Default: 30
- convergence
- Percent convergence
- Parameter format: float
- Options: 0-100
- Default: 98.0
- separation
- Cluster separation
- Parameter format: float
- Default: 0.0
- outputGeoTiffType
- Type of output GeoTIFF file. The output Format Type is specified as GeoTIFF
- Parameter format: string
- Options: Byte,Int16,UInt16,UInt32,Int32,Float32,Float64,CInt16,CInt32,CFloat32,CFloat64
Response Parameters:
- returnURL
- URL of output raster map to hold classification results
- returnFormat
- Format of output raster map
- Default: GeoTIFF
- reportURL
- URL of an output file to contain final report
- Default: text
- reportFormat
- Format of output file to contain final report
- Default: TEXT
For further informations
ServiceLocation
WSDL
JavaInterface
See also GRASS commands
i.cluster
i.maxlik
|
|