![](../logo.png)
Binary classification of a single-band image based on a threshold value
Source:R/classify_image_binary.R
classify_image_binary.Rd
Classify a single-band image such as a spectral index or greyscale raster derived from satellite data. If a threshold value is not specified, the Otsu's threshold can be calculated and used for classification.
Usage
classify_image_binary(
image,
threshold = "otsu",
range = NULL,
levels = 256,
file = NULL,
...
)
Arguments
- image
Single band raster to be classified (
SpatRaster
object fromlibrary(terra)
), or a file path to the image to be imported (terra::rast()
will be used).- threshold
Either a numeric value for a manually-specified threshold, or
"otsu"
to calculate the threshold via Otsu's method. Defaults to"otsu"
.- range
Numeric vector (of length 2) specifying the histogram range to be used for Otsu's thresholding (only relevant if
threshold = "otsu"
). Defaults to the minimum and maximum values of the imported raster.- levels
Number of histogram bins used to calculate the threshold value (only relevant if
threshold = "otsu"
). Typically based on the bit depth of the image (e.g. 8-bit image has2^8
=256
levels). Defaults to256
.- file
File path to export output raster (optional). Defaults to
NULL
.- ...
Other arguments that may be supplied to
terra::writeRaster()
.
See also
threshold_otsu()
Internal function used to calculate threshold value via Otsu's method.
Examples
if (FALSE) {
ndvi_mosaic <- system.file("extdata", "ndvi_mosaic.tif",
package="biodivercity")
terra::plot(ndvi_mosaic) # examine continuous raster
ndvi_classified <- classify_image_binary(image = ndvi_mosaic)
terra::plot(ndvi) # examine classified raster
}