sits (version 0.13.0)

sits_smooth: Post-process a classified data raster probs using smoothing

Description

Takes a set of classified raster layers with probabilities, whose metadata is]created by sits_cube, and applies a smoothing function. There are three options, defined by the "type" parameter:

• "bayes": Use a bayesian smoother

• "gaussian": Use a gaussian smoother

• "bilateral: Use a bilateral smoother

Usage

sits_smooth(cube, type = "bayes", ...)
# S3 method for bayes
sits_smooth(
  cube,
  type = "bayes",
  ...,
  window_size = 5,
  smoothness = 20,
  covar = FALSE,
  multicores = 2,
  memsize = 4,
  output_dir = tempdir(),
  version = "v1"
)
# S3 method for gaussian
sits_smooth(
  cube,
  type = "gaussian",
  ...,
  window_size = 5,
  sigma = 1,
  multicores = 2,
  memsize = 4,
  output_dir = tempdir(),
  version = "v1"
)
# S3 method for bilateral
sits_smooth(
  cube,
  type = "bilateral",
  ...,
  window_size = 5,
  sigma = 8,
  tau = 0.1,
  multicores = 2,
  memsize = 4,
  output_dir = tempdir(),
  version = "v1"
)

Arguments

cube

Probability data cube

type

Type of smoothing

...

Parameters for specific functions

window_size

Size of the neighbourhood.

smoothness

Estimated variance of logit of class probabilities (Bayesian smoothing parameter). It can be either a matrix or a scalar.

covar

a logical argument indicating if a covariance matrix must be computed as the prior covariance for bayesian smoothing.

multicores

Number of cores to run the smoothing function

memsize

Maximum overall memory (in GB) to run the smoothing.

output_dir

Output directory for image files

version

Version of resulting image (in the case of multiple tests)

sigma

Standard deviation of the spatial Gaussian kernel (for gaussian and bilateral smoothing)

tau

Standard deviation of the class probs value (for bilateral smoothing)

Value

A tibble with metadata about the output raster objects.

References

K. Schindler, "An Overview and Comparison of Smooth Labeling Methods for Land-Cover Classification", IEEE Transactions on Geoscience and Remote Sensing, 50 (11), 4534-4545, 2012 (for gaussian and bilateral smoothing)

Examples

# NOT RUN {
# Retrieve the samples for Mato Grosso
# select band "ndvi"

samples_ndvi <- sits_select(samples_modis_4bands, bands = "NDVI")

# select a random forest model
rfor_model <- sits_train(samples_ndvi, sits_rfor(num_trees = 500))

# create a data cube based on the information about the files
data_dir <- system.file("extdata/raster/mod13q1", package = "sits")
cube <- sits_cube(
    source = "LOCAL",
    name = "sinop-2014",
    satellite = "TERRA",
    sensor = "MODIS",
    data_dir = data_dir,
    delim = "_",
    parse_info = c("X1", "X2", "tile", "band", "date")
)

# classify the raster image
probs_cube <- sits_classify(cube,
    ml_model = rfor_model,
    output_dir = tempdir(),
    memsize = 4, multicores = 2
)

# smooth the result with a bayesian filter
bayes_cube <- sits_smooth(probs_cube,
     type = "bayes", output_dir = tempdir()
)

# smooth the result with a gaussian filter
gauss_cube <- sits_smooth(probs_cube,
    type = "gaussian", output_dir = tempdir()
)

# smooth the result with a bilateral filter
bil_cube <- sits_smooth(probs_cube,
    type = "bilateral", output_dir = tempdir()
)
# }
# NOT RUN {
# }