EnhanceCrops Task

AgEnhanceCrops Task

This task is a preprocessing step that enhances crops in a single-band raster. The result can be passed to ENVIAgCropCount or AgCountAndRasterizeCrops Task. You can optionally set minimum and maximum pixel value thresholds on the input raster. The task then inverts the remaining pixel values, unless you choose to disable inversion.

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 subset consisting of the green band only.
Masks out pixel values greater than 90 in the green band. These are primarily soil pixels that need to be masked out.
Inverts the thresholded green band image to make the citrus trees appear bright.
Displays the result.

; 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)

; Define a spectral subset consisting of

; the green band

GreenBand = ENVISubsetRaster(Raster, BANDS=1)

; Get the task from the catalog of ENVITasks

Task = ENVITask('AgEnhanceCrops')

; Define task inputs

Task.INPUT_RASTER = GreenBand

Task.INPUT_MAX = 90 ; to mask out bright soil pixels

Task.INVERSE='true'

; Run the task

Task.Execute

; Get the collection of objects currently in the Data Manager

DataColl = e.Data

; Add the output to the Data Manager

DataColl.Add, Task.OUTPUT_RASTER

; Display the result

View = e.GetView()

Layer = View.CreateLayer(Task.OUTPUT_RASTER)

The resulting image still contains shadows, which have a similar brightness to the citrus trees in the inverted green band. It is difficult to remove these pixels without also removing vegetation pixels. See More Examples for a different method of isolating the citrus trees.

Syntax

Result = ENVITask('AgEnhanceCrops')

Input properties (Set, Get): INPUT_MAX, INPUT_MIN, INPUT_RASTER, INVERSE, OUTPUT_RASTER_URI

Output properties (Get only): 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

INPUT_MAX (optional)

Specify a maximum data value. Pixels greater than this value are set to NaN and will be ignored in subsequent processing. An example is setting a maximum value to remove shadows or bright soil pixels in an inverted green band image. These features have a similar brightness value to healthy vegetation and should be removed to reduce confusion in crop-counting tasks.

INPUT_MIN (optional)

Specify a minimum data value. Pixels less than this value are set to NaN and will be ignored in subsequent processing. An example is setting a mimimum value to remove dark shadows from a spectral index image (such as NDVI) or from a single-band image where INVERSE = 'false'.

INPUT_RASTER (required)

Specify a single-band raster. If you have a multispectral dataset, you must create a spectral subset consisting of only one band.

INVERSE (optional)

Set this property to true (the default value) to invert the data. An example is to invert the values in a green band.

OUTPUT_RASTER

This is a reference to the output raster of filetype ENVI.

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.

More Examples

This example performs the following steps:

Opens an orthophoto of a citrus orchard.
Creates an Iron Oxide spectral index image to highlight soil pixels.
Masks out pixel values greater than 1.092. These are primarily soil pixels.
Masks out pixel values lower than 0.322. These are primarily shadow pixels.
Inverts the thresholded Iron Oxide image to make the citrus trees appear bright.
Displays the result.

; 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)

; Create an Iron Oxide spectral index raster

indexRaster = ENVISpectralIndexRaster(Raster, 'Iron Oxide')

; Get the task from the catalog of ENVITasks

Task = ENVITask('AgEnhanceCrops')

; Define task inputs

Task.INPUT_RASTER = indexRaster

Task.INPUT_MIN = 0.322

Task.INPUT_MAX = 1.092

Task.INVERSE = 'true'

; Define outputs

Task.OUTPUT_RASTER_URI = e.GetTemporaryFilename()

; Run the task

Task.Execute

; Get the collection of objects currently in the Data Manager

DataColl = e.Data

; Add the output to the Data Manager

DataColl.Add, Task.OUTPUT_RASTER

; Display the result

View = e.GetView()

Layer = View.CreateLayer(Task.OUTPUT_RASTER)

Version History

Crop Science 1.0

Introduced