sits (version 1.4.1)

sits_view: View data cubes and samples in leaflet

Description

Uses leaflet to visualize time series, raster cube and classified images

Usage

sits_view(x, ...)
# S3 method for sits
sits_view(x, ..., legend = NULL, color_palette = "Harmonic")
# S3 method for data.frame
sits_view(x, ..., legend = NULL, color_palette = "Harmonic")
# S3 method for som_map
sits_view(x, ..., id_neurons, legend = NULL, color_palette = "Harmonic")
# S3 method for raster_cube
sits_view(
  x,
  ...,
  band = NULL,
  red = NULL,
  green = NULL,
  blue = NULL,
  tiles = x$tile,
  dates = NULL,
  class_cube = NULL,
  legend = NULL,
  color_palette = "RdYlGn",
  segments = NULL,
  view_max_mb = NULL
)
# S3 method for uncertainty_cube
sits_view(
  x,
  ...,
  tiles = x$tile,
  class_cube = NULL,
  legend = NULL,
  color_palette = "Blues",
  segments = NULL,
  view_max_mb = NULL
)
# S3 method for class_cube
sits_view(
  x,
  ...,
  tiles = NULL,
  legend = NULL,
  color_palette = "Spectral",
  segments = NULL,
  view_max_mb = NULL
)
# S3 method for probs_cube
sits_view(
  x,
  ...,
  tiles = x$tile,
  class_cube = NULL,
  legend = NULL,
  view_max_mb = NULL,
  color_palette = "YlGnBu"
)
# S3 method for default
sits_view(x, ...)

Value

A leaflet object containing either samples or data cubes embedded in a global map that can be visualized directly in an RStudio viewer.

Arguments

x

Object of class "sits", "data.frame", "som_map", "raster_cube" or "classified image".

...

Further specifications for sits_view.

legend

Named vector that associates labels to colors.

color_palette

Palette provided in the configuration file.

id_neurons

Neurons from the SOM map to be shown.

band

For plotting grey images.

red

Band for red color.

green

Band for green color.

blue

Band for blue color.

tiles

Tiles to be plotted (in case of a multi-tile cube).

dates

Dates to be plotted.

class_cube

Classified cube to be overlayed on top on image.

segments

Segment list produced by sits_segment

view_max_mb

Maximum size of leaflet to be visualized

Author

Gilberto Camara,

Examples

if (sits_run_examples()) {
    # view samples
    sits_view(cerrado_2classes)
.    # create a local data cube
    data_dir <- system.file("extdata/raster/mod13q1", package = "sits")
    modis_cube <- sits_cube(
        source = "BDC",
        collection = "MOD13Q1-6",
        data_dir = data_dir
    )
    # view the data cube
    sits_view(modis_cube,
        band = "NDVI"
    )
    # train a model
    rf_model <- sits_train(samples_modis_ndvi, sits_rfor())
.    # classify the cube
    modis_probs <- sits_classify(
        data = modis_cube,
        ml_model = rf_model,
        output_dir = tempdir()
    )
    # view the probs
    sits_view(modis_probs)
    # generate a map
    modis_label <- sits_label_classification(
        modis_probs,
        output_dir = tempdir()
    )
.    # view the classified map
    sits_view(modis_label)
.    # view the classified map with the B/W image
    sits_view(modis_cube,
        band = "NDVI",
        class_cube = modis_label,
        dates = sits_timeline(modis_cube)[[1]]
    )
    # view the classified map with the RGB image
    sits_view(modis_cube,
        red = "NDVI", green = "NDVI", blue = "NDVI",
        class_cube = modis_label,
        dates = sits_timeline(modis_cube)[[1]]
    )
    # create an uncertainty cube
    modis_uncert <- sits_uncertainty(
        cube = modis_probs,
        output_dir = tempdir()
    )
    # view the uncertainty cube
    sits_view(modis_uncert)

    # segment the image
    segments <- sits_segment(
        cube = modis_cube,
        tile = "012010",
        bands = "NDVI",
        date = sits_timeline(modis_cube)[1],
        seg_fn = sits_slic(step = 20)
    )
    # view image and segments
    sits_view (
        modis_cube,
        band = "NDVI",
        segments = segments
    )
    # view image, classified image and segments
    sits_view (
        modis_cube,
        red = "NDVI",
        green = "NDVI",
        blue = "NDVI",
        class_cube = modis_label,
        segments = segments
    )
    # view B/W image, classified image and segments
    sits_view (
        modis_cube,
        band = "NDVI",
        class_cube = modis_label,
        segments = segments
    )
    # get the average value per segment
    samples_seg <- sits_get_data(
        cube = modis_cube,
        samples = segments
    )
    # train a model
    tcnn_model <- sits_train(samples_modis_ndvi, sits_tempcnn())
    # classify the segments
    seg_class <- sits_classify(
        data = samples_seg,
        ml_model = tcnn_model
    )

    # add a column to the segments by class
    segments <- sits_join_segments(
        data = seg_class,
        segments = segments
    )
    # view image and classified segments
    sits_view (
        modis_cube,
        band = "NDVI",
        segments = segments
    )
    # view image, classified image and segments
    sits_view (
        modis_cube,
        red = "NDVI",
        green = "NDVI",
        blue = "NDVI",
        class_cube = modis_label,
        segments = segments
    )
}