CalculateAndRasterizeCropMetrics Task

AgCalculateAndRasterizeCropMetrics Task

This task calculates statistics from a single-band raster and an associated ENVIAgCrops object. It creates a classification raster showing the relative means of crops or a grayscale raster showing actual mean values of crops. For example, if the input raster is a vegetation index such as NDVI, the crop means describe the health of the crops.

AgCalculateAndRasterizeCropMetrics is a metatask that automatically runs the following tasks:

You can run AgCropCountTask or AgCountAndRasterizeCropsTask to create the ENVIAgCrops object that is required for this task. Or, you can use an ENVIAgCrops file that you created and saved earlier.

This task requires a separate license for the ENVI Crop Science Module; contact your sales representative for more information.

Example

This example performs the following steps.

Opens an orthophoto of a citrus orchard.
Creates a spectral index raster to make the citrus trees bright against the background. A Normalized Difference Vegetation Index (NDVI) works well in this case. NDVI will be used for crop counting and for calculating metrics in this example.

Tip: See SpectralIndex Task for a list of spectral indices. You can run QuerySpectralIndices Task to see what indices are available for your particular image.

Runs ENVIAgCropCount to count the trees and to create an ENVIAgCrops object.
Runs AgCalculateAndRasterizeCropMetrics task, using the NDVI image as the basis for calculating metrics.
Displays a classification raster showing relative NDVI means of the citrus trees.
Prints the range of crop NDVI values in the entire image.

; Start the application

e = ENVI()

; Open an input file

File = Filepath('CitrusOrthophoto.dat', $

  Subdir=['data','crop_science'], $

  Root_Dir=e.Root_Dir)

Raster = e.OpenRaster(File)

; Preprocess the image so that crops are bright.

NDVIImage = ENVISpectralIndexRaster(Raster, 'NDVI')

; Count the crops and output an ENVIAgCrops object

outCrops = ENVIAgCropCount(NDVIImage, 2.0, 5.0, $

  GAUSSIAN_FACTOR = 0, $

  /INCLUDE_EDGES, $

  INTENSITY_THRESHOLD = 0.8, $

  NUMBER_OF_INCREMENTS = 4, $

  PERCENT_OVERLAP = 100.0)

; Get the metrics task from the catalog of ENVITasks

Task = ENVITask('AgCalculateAndRasterizeCropMetrics')

; Define inputs

Task.INPUT_CROPS = outCrops

Task.INPUT_RASTER = NDVIImage

; Run the task

Task.Execute

; Get the collection of objects currently in the Data Manager

DataColl = e.Data

; Add the output to the data collection

DataColl.Add, Task.OUTPUT_RASTER

; Display the result

View = e.GetView()

Layer = View.CreateLayer(Task.OUTPUT_RASTER)

View.Zoom, /FULL_EXTENT

; Print the range of NDVI values

crops = Task.OUTPUT_CROPS

Print, 'Minimum NDVI value for entire image: ',MIN(crops.CROP_MIN)

Print, 'Maximum NDVI value for entire image: ',MAX(crops.CROP_MAX)

Syntax

Result = ENVITask('AgCalculateAndRasterizeCropMetrics')

Input properties (Set, Get): CLASSIFICATION, INPUT_CROPS, INPUT_RASTER, OUTPUT_CROPS_URI, OUTPUT_METRIC, OUTPUT_RASTER_URI

Output properties (Get only): OUTPUT_CROPS, OUTPUT_RASTER

Properties marked as "Set" are those that you can set to specific values. You can also retrieve their current values any time. Properties marked as "Get" are those whose values you can retrieve but not set.

Methods

This task inherits the following methods from ENVITask:

Properties

This task inherits the following properties from ENVITask:

COMMUTE_ON_DOWNSAMPLE

CLASSIFICATION (optional)

Set this property to true (the default value) to create a classification raster where crops are colored according to relative means. For example, a dark green polygon corresponds to a crop with a higher mean value than light-green, yellow, and red polygons. The resulting raster will look similar to the following:

If you set the CLASSIFICATION property to false, the output will be a grayscale raster that is based on the actual mean values of the crops; for example:

INPUT_CROPS (required)

Specify an input ENVIAgCrops object. You can run AgCropCount Task or AgCountAndRasterizeCrops Task to create an ENVIAgCrops object before running this task. Or, you can use an ENVIAgCrops file that you created and saved earlier.

INPUT_RASTER (required)

Specify a single-band raster from which crop metrics will be computed. A common example is a spectral index raster such as Normalized Difference Vegetation Index (NDVI).

OUTPUT_CROPS (required)

This is a reference to the output crop data.

OUTPUT_CROPS_URI (optional)

Specify a string with the fully qualified path and filename for OUTPUT_CROPS. If you do not specify this property, the output crop file is only temporary. Once the crop file has no remaining references, ENVI deletes the temporary file.

OUTPUT_METRIC (optional)

Set this property to one of the following strings, indicating the metric that the output raster will be based on:

Crop Mean (default)
Crop Maximum
Crop Minimum
Crop Standard Deviation
Radius

OUTPUT_RASTER

This is a reference to the output crops classification raster or grayscale raster.

OUTPUT_RASTER_URI (optional)

Specify a string with the fully qualified filename and path of the associated OUTPUT_RASTER. If you do not specify this property, or set it to an exclamation symbol (!), a temporary file will be created.

Version History

Crop Science 1.0	Introduced
Crop Science 1.1	Added Crop Minimum, Crop Maximum, Crop Standard Deviation, and Radius options to OUTPUT_METRIC.