cloud_fill_simple: Cloud fill using a simple linear model approach

In yinscapital/sat-locat-reference-team-lucc: TEAM land use and cover change data processing toolkit

Description

This algorithm fills clouds using a simple approach in which the value of each clouded pixel is calculated using a linear model. The script develops a separate linear model (with slope and intercept) for each band and each cloud. For each cloud, and each image band, the script finds all pixels clear in both the cloudy and fill images, and calculates a regression model in which pixel values in the fill image are the independent variable, and pixel values in the clouded image are the dependent variable. The script then uses this model to predict pixel values for each band in each cloud in the clouded image.

Usage

cloud_fill_simple(cloudy, clear, cloud_mask, dims, num_class, cloud_nbh, DN_min,
  DN_max, verbose = FALSE)

Arguments

cloudy	the cloudy image as a matrix, with pixels in columns (in column-major order) and with number of columns equal to number of bands
clear	the clear image as a matrix, with pixels in columns (in column-major order) and with number of columns equal to number of bands
cloud_mask	the cloud mask image as a vector (in column-major order), with clouds coded with unique integer codes starting at 1, and with areas that are clear in both images coded as 0. Areas that are missing in the clear image, should be coded as -1.
dims	the dimensions of the cloudy image as a length 3 vector: (rows, columns, bands)
num_class	set the estimated number of classes in image
cloud_nbh	the range of cloud neighborhood (in pixels)
DN_min	the minimum valid DN value
DN_max	the maximum valid DN value
verbose	whether to print detailed status messages

Details

This function is called by the cloud_remove function. It is not intended to be used directly.

Value

array with cloud filled image with dims: cols, rows, bands parameter, containing the selected textures measures

yinscapital/sat-locat-reference-team-lucc documentation built on May 14, 2019, 11:09 a.m.