Sample Selection

Selects samples from a training vector data set.

Detailed description

The application selects a set of samples from geometries intended for training (they should have a field giving the associated class).

First of all, the geometries must be analyzed by the PolygonClassStatistics application to compute statistics about the geometries, which are summarized in an xml file. Then, this xml file must be given as input to this application (parameter instats).

The input support image and the input training vectors shall be given in parameters ‘in’ and ‘vec’ respectively. Only the sampling grid (origin, size, spacing)will be read in the input image. There are several strategies to select samples (parameter strategy) :

  • smallest (default) : select the same number of sample in each class so that the smallest one is fully sampled.
  • constant : select the same number of samples N in each class (with N below or equal to the size of the smallest class).
  • byclass : set the required number for each class manually, with an input CSV file (first column is class name, second one is the required samples number).
There is also a choice on the sampling type to performs :
  • periodic : select samples uniformly distributed
  • random : select samples randomly distributed

Once the strategy and type are selected, the application outputs samples positions(parameter out).

The other parameters to look at are :
  • layer : index specifying from which layer to pick geometries.
  • field : set the field name containing the class.
  • mask : an optional raster mask can be used to discard samples.
  • outrates : allows outputting a CSV file that summarizes the sampling rates for each class.

As with the PolygonClassStatistics application, different types of geometry are supported : polygons, lines, points. The behavior of this application is different for each type of geometry :

  • polygon: select points whose center is inside the polygon
  • lines : select points intersecting the line
  • points : select closest point to the provided point

Parameters

This section describes in details the parameters available for this application. Table [1] presents a summary of these parameters and the parameters keys to be used in command-line and programming languages. Application key is SampleSelection .

[1]Table: Parameters table for Sample Selection.
Parameter Key Parameter Type Parameter Description
in Input image Input image
mask Input image Input image
vec Input File name Input File name
out Output File name Output File name
instats Input File name Input File name
outrates Output File name Output File name
sampler Choices Choices
sampler periodic Choice Periodic sampler
sampler random Choice Random sampler
sampler.periodic.jitter Int Int
strategy Choices Choices
strategy byclass Choice Set samples count for each class
strategy constant Choice Set the same samples counts for all classes
strategy smallest Choice Set same number of samples for all classes, with the smallest class fully sampled
strategy all Choice Take all samples
strategy.byclass.in Input File name Input File name
strategy.constant.nb Int Int
field String String
layer Int Int
ram Int Int
rand Int Int
inxml XML input parameters file XML input parameters file
outxml XML output parameters file XML output parameters file

InputImage Support image that will be classified.

InputMask Validity mask (only pixels corresponding to a mask value greater than 0 will be used for statistics).

Input vectors Input geometries to analyse.

Output vectors Output resampled geometries.

Input Statistics Input file storing statistics (XML format).

Output rates Output rates (CSV formatted).

Sampler type Type of sampling (periodic, pattern based, random). Available choices are:

  • Periodic sampler : Takes samples regularly spaced
  • Jitter amplitude : Jitter amplitude added during sample selection (0 = no jitter).
  • Random sampler : The positions to select are randomly shuffled.
Sampling strategy
Available choices are:
  • Set samples count for each class : Set samples count for each class
  • Number of samples by class : Number of samples by class (CSV format with class name in 1st column and required samples in the 2nd.
  • Set the same samples counts for all classes : Set the same samples counts for all classes
  • Number of samples for all classes : Number of samples for all classes.
  • Set same number of samples for all classes, with the smallest class fully sampled : Set same number of samples for all classes, with the smallest class fully sampled
  • Take all samples : Take all samples

Field Name Name of the field carrying the class name in the input vectors.

Layer Index Layer index to read in the input vector file.

Available RAM (Mb) Available memory for processing (in MB).

set user defined seed Set specific seed. with integer value.

Load otb application from xml file Load otb application from xml file.

Save otb application to xml file Save otb application to xml file.

Example

To run this example in command-line, use the following:

otbcli_SampleSelection -in support_image.tif -vec variousVectors.sqlite -field label -instats apTvClPolygonClassStatisticsOut.xml -out resampledVectors.sqlite

To run this example from Python, use the following code snippet:

#!/usr/bin/python

# Import the otb applications package
import otbApplication

# The following line creates an instance of the SampleSelection application
SampleSelection = otbApplication.Registry.CreateApplication("SampleSelection")

# The following lines set all the application parameters:
SampleSelection.SetParameterString("in", "support_image.tif")

SampleSelection.SetParameterString("vec", "variousVectors.sqlite")

SampleSelection.SetParameterString("field", "label")

SampleSelection.SetParameterString("instats", "apTvClPolygonClassStatisticsOut.xml")

SampleSelection.SetParameterString("out", "resampledVectors.sqlite")

# The following line execute the application
SampleSelection.ExecuteAndWriteOutput()

Limitations

None

Authors

This application has been written by OTB-Team.