split_classes: Split classes in a training dataset using normal mixture...

Description Usage Arguments

View source: R/split_classes.R

Description

This function can be used to aid in classifying spectrally diverse classes by splitting the input classes into subclasses using a clustering algorithm. After classification, these subclasses are merged back into their original parent classes. For example, the training data for an agriculture class might have both fallow and planted fields in the training data, or fields planted with different crops that are spectrally dissimilar. This function can be used to automatically split the agriculture class into a number of subclasses. The classifier is then run on this larger set of classes, and following classification, these subclasses can all be merged together into a single overall agriculture class.

Usage

1
split_classes(train_data, split_levels, verbose = FALSE)

Arguments

train_data

a link{pixel_data} object

split_levels

(optional) a list giving the names of the levels to split. If missing, all levels will be split.

verbose

whether to report status while running


azvoleff/teamlucc documentation built on June 4, 2017, 12:08 a.m.