3D Analyst Tools ArcToolbox

Train Random Trees Classifier, Support Vector Machine Classifier and Update Accuracy Assessment Points Tools

Train Random Trees Classifier

How to use Train Random Trees Classifier Tool in Arc Toolbox??

Train Random Trees Classifier

Path to access the tool

:

Train Random Trees Classifier Tool, Segmentation and Classification Toolset, Spatial Analyst Tools Toolbox

 

Train Random Trees Classifier

Generates an Esri classifier definition (.ecd) file using the Random Trees classification method.

The random trees classifier is a powerful technique for image classification that is resistant to overfitting and can work with segmented images and other ancillary raster datasets. For standard image inputs, the tool accepts multiple-band imagery with any bit depth, and it will perform the Random Trees classification on a pixel basis or segment, based on the input training feature file.

1.    Input Raster

The raster dataset to classify.

You can use any Esri-supported raster dataset. Options include a 3-band, 8-bit segmented raster dataset, where all the pixels in the same segment have the same color. The input can also be a 1-band, 8-bit, grayscale segmented raster.

2.    Input Training Sample Features

The training sample file or layer that delineates your training sites.

These can be either shapefiles or feature classes that contain your training samples. The following field names are required in the training sample file:

1. classname—A text field indicating the name of the class category.
2. classvalue—A long integer field containing the integer value for each class category.

3.    Output Classifier Definition File

A JSON file that contains attribute information, statistics, or other information needed for the classifier. A file with an .ecd extension is created.

4.    Additional Input Raster (optional)

Incorporate ancillary raster datasets, such as a multispectral image or a DEM, to generate attributes and other required information for classification. This parameter is optional.

5.    Max Number of Trees (optional)

The maximum number of trees in the forest. Increasing the number of trees will lead to higher accuracy rates, although this improvement will level off eventually. The number of trees increases the processing time linearly.

6.    Max Tree Depth (optional)

The maximum depth of each tree in the forest. Depth is another way of saying the number of rules each tree is allowed to create to come to a decision. Trees will not grow any deeper than this setting.

7.    Max Number Of Samples Per Class (optional)

The maximum number of samples to use for defining each class.

The default value of 1000 is recommended when the inputs are nonsegmented rasters. A value that is less than or equal to 0 means that the system will use all the samples from the training sites to train the classifier.

8.    Segment Attributes Used (optional)

Specifies the attributes to be included in the attribute table associated with the output raster.

1. COLOR—The RGB color values are derived from the input raster, on a per-segment basis.
2. MEAN—The average digital number (DN), derived from the optional pixel image, on a per-segment basis.
3. STD—The standard deviation, derived from the optional pixel image, on a per-segment basis.
4. COUNT—The number of pixels comprising the segment, on a per-segment basis.
5. COMPACTNESS—The degree to which a segment is compact or circular, on a per-segment basis. The values range from 0 to 1, where 1 is a circle.
6. RECTANGULARITY—The degree to which the segment is rectangular, on a per-segment basis. The values range from 0 to 1, where 1 is a rectangle.

This parameter is only active if the Segmented key property is set to true on the input raster. If the only input to the tool is a segmented image, the default attributes are COLOR, COUNT, COMPACTNESS, and RECTANGULARITY. If an Additional Input Raster is included as an input with a segmented image, MEAN and STD are also available attributes.

Train Support Vector Machine Classifier

How to use Train Support Vector Machine Classifier Tool in Arc Toolbox??

Train Support Vector Machine Classifier

Path to access the tool

:

Train Support Vector Machine Classifier Tool, Segmentation and Classification Toolset, Spatial Analyst Tools Toolbox

 

Train Support Vector Machine Classifier

Generates an Esri classifier definition (.ecd) file using the Support Vector Machine (SVM) classification definition.

1.    Input Raster

The raster dataset to classify.

The preferred input is a 3-band, 8-bit segmented raster dataset, where all the pixels in the same segment have the same color. The input can also be a 1-band, 8-bit grayscale segmented raster. If no segmented raster is available, you can use any Esri-supported raster dataset.

2.    Input Training Sample Features

The training sample file or layer that delineates your training sites.

These can be either shapefiles or feature classes that contain your training samples. The following field names are required in the training sample file:

1. classname—A text field indicating the name of the class category.
2. classvalue—A long integer field containing the integer value for each class category.

3.    Output Classifier Definition File

The output JSON file that contains attribute information, statistics, hyperplane vectors, and other information for the classifier. An .ecd file is created.

4.    Additional Input Raster (optional)

Incorporate ancillary raster datasets, such as a multispectral image or a DEM, to generate attributes and other required information for classification. This parameter is optional.

5.    Max Number Of Samples Per Class (optional)

The maximum number of samples to use for defining each class.

The default value of 500 is recommended when the inputs are nonsegmented rasters. A value that is less than or equal to 0 means that the system will use all the samples from the training sites to train the classifier.

6.    Segment Attributes Used (optional)

Specifies the attributes to be included in the attribute table associated with the output raster.

1. COLOR—The RGB color values are derived from the input raster, on a per-segment basis.
2. MEAN—The average digital number (DN), derived from the optional pixel image, on a per-segment basis.
3. STD—The standard deviation, derived from the optional pixel image, on a per-segment basis.
4. COUNT—The number of pixels comprising the segment, on a per-segment basis.
5. COMPACTNESS—The degree to which a segment is compact or circular, on a per-segment basis. The values range from 0 to 1, where 1 is a circle.
6. RECTANGULARITY—The degree to which the segment is rectangular, on a per-segment basis. The values range from 0 to 1, where 1 is a rectangle.

This parameter is only active if the Segmented key property is set to true on the input raster. If the only input to the tool is a segmented image, the default attributes are COLOR, COUNT, COMPACTNESS, and RECTANGULARITY. If an Additional Input Raster is included as an input with a segmented image, MEAN and STD are also available attributes.

Update Accuracy Assessment Points

How to use Update Accuracy Assessment Points Tool in Arc Toolbox??

Update Accuracy Assessment Points

Path to access the tool

:

Update Accuracy Assessment Points Tool, Segmentation and Classification Toolset, Spatial Analyst Tools Toolbox

 

Update Accuracy Assessment Points

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

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

1.    Input Raster Or Feature Class

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 (single band, integer data type) or the training polygon output from an ArcMap image classification toolbar.

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.

2.    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 will be updated from the input raster or feature class data.

3.    Output Accuracy Assessment Points

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

4.    Target Field (optional)

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

1. CLASSIFIED—The input is a classified image. This is the default.
2. GROUND_TRUTH—The input is reference data.