Update Accuracy Assessment Points (Image Analyst)

Available with Spatial Analyst license.

Available with Image Analyst license.

Summary

Updates the Target field in the attribute table to compare reference points to the classified image.

Accuracy assessment uses known points to assess the validity of the classification model.

Usage

  • Use this tool to update the attribute table of a feature class that represents accuracy assessment points. If you created the feature class using the Create Accuracy Assessment Points tool, a GROUND_TRUTH field and a CLASSIFIED field are included in the table. This tool can start with the reference data and compare it to the classified output, or it can start with the classified output and compare it to the reference data.

    You can then compare the two fields using the Compute Confusion Matrix tool.

  • The accuracy assessment workflow usually uses the following three tools in this order: Create Accuracy Assessment Points, Update Accuracy Assessment Points, and Compute Confusion Matrix.

  • When a polygon feature class is used for training or accuracy assessment, the feature class must have a Classvalue or value field that has a unique integer value for each class. For example, a polygon feature class with three different classes can have values such as [1, 2, 3] or [10, 20, 40].

  • You can manually update the GROUND_TRUTH field to change or identify a set of points.

  • When the Input Raster or Feature Class Data parameter value is a multidimensional raster, the time dimension (StdTime field) will be used automatically. If a fourth dimension exists (for example, Z field), the first dimension value will be used. You can use the Make Multidimensional Raster Layer tool or the Subset Multidimensional Raster tool to configure the input.

Parameters

LabelExplanationData Type
Input Raster or Feature Class Data

The input classification image or other thematic GIS reference data. The input can be a raster or feature class.

Typical data is a classification image of a single band, integer data type.

If using polygons as input, only use those that are not used as training samples. You can also use land-cover data in shapefile or feature class format.

Raster Layer; Mosaic Layer; Feature Layer
Input Accuracy Assessment Points

The point feature class providing the accuracy assessment points to be updated.

All points from this input will be copied to the updated output feature class, and the Target Field parameter value will be updated from the input raster or feature class data.

Feature Layer
Output Accuracy Assessment Points

The output point feature class that contains the updated random point field for accuracy assessment purposes.

Feature Class
Target Field
(Optional)

Specifies whether the input data is a classified image or ground truth data.

  • ClassifiedThe input is a classified image. This is the default.
  • Ground truthThe input is reference data.
String
Dimension Field for Feature Class
(Optional)

The dimension field for the Input Accuracy Assessment Points parameter value. The assessment points will be updated based on the matching dimension values with this field.

Field
Dimension Field for Test Points
(Optional)

The dimension field in the Input Accuracy Assessment Points parameter value. Input data with identical dimension values will be used to update corresponding points.

When the Input Raster or Feature Class Data parameter value is a multidimensional raster, rasters with dimension values that match the dimension field in the test points will be used in updating. The multidimensional raster is expected to have one time dimension (StdTime field). Otherwise, the first dimension will be used to match the dimension field of the test points.

Field

UpdateAccuracyAssessmentPoints(in_class_data, in_points, out_points, {target_field}, {polygon_dimension_field}, {point_dimension_field})
NameExplanationData Type
in_class_data

The input classification image or other thematic GIS reference data. The input can be a raster or feature class.

Typical data is a classification image of a single band, integer data type.

If using polygons as input, only use those that are not used as training samples. You can also use land-cover data in shapefile or feature class format.

Raster Layer; Mosaic Layer; Feature Layer
in_points

The point feature class providing the accuracy assessment points to be updated.

All points from this input will be copied to the updated output feature class, and the target_field parameter value will be updated from the input raster or feature class data.

Feature Layer
out_points

The output point feature class that contains the updated random point field for accuracy assessment purposes.

Feature Class
target_field
(Optional)

Specifies whether the input data is a classified image or ground truth data.

  • CLASSIFIEDThe input is a classified image. This is the default.
  • GROUND_TRUTHThe input is reference data.
String
polygon_dimension_field
(Optional)

The dimension field for the in_points parameter value. The assessment points will be updated based on the matching dimension values with this field.

Field
point_dimension_field
(Optional)

The dimension field in the in_points parameter value. Input data with identical dimension values will be used to update corresponding points.

When the in_class_data parameter value is a multidimensional raster, rasters with dimension values that match the dimension field in the test points will be used in updating. The multidimensional raster is expected to have one time dimension (StdTime field). Otherwise, the first dimension will be used to match the dimension field of the test points.

Field

Code sample

UpdateAccuracyAssessmentPoints example 1 (stand-alone script)

This example updates the points used for accuracy assessment.

import arcpy
from arcpy.ia import *

# Check out the ArcGIS Image Analyst extension license
arcpy.CheckOutExtension("ImageAnalyst")

UpdateAccuracyAssessmentPoints("c:\\test\\aapnt1.shp", "c:\\test\\grndtru.tif", "c:\\test\\aapnt2.shp", "GROUND_TRUTH")

Environments

This tool does not use any geoprocessing environments.

Related topics