aoiMaker {nnDiag} | R Documentation |
The purpose of this function is to create Areas of Interest (AOI) from a larger image that include a minimum number of reference set elements. The object created can then be used in kNN diagnostic tests.
aoiMaker(ref.coords, num.aoi, image, mask = NULL, aoi.size = 1000, min.points = 25, seed = NULL, verbose = TRUE)
ref.coords |
matrix of reference point coordinates |
num.aoi |
a single integer, number of AOIs desired |
image |
the image to make AOIs from, as an object of class GDALReadOnlyDataset |
mask |
optional mask image, as an object of class GDALReadOnlyDataset |
aoi.size |
a single integer, size of the AOI in pixels |
min.points |
a single integer, minimum number of reference points in each AOI desired |
seed |
a single value, interpreted as an integer |
verbose |
logical indicating whether to display a progress bar |
The ref.coords
must be a two column matrix with an X and Y
location.
Both the image
and mask
have to be in the class
"GDALReadOnlyDataset"
. This can be achieved by using the
command GDAL.open
from the package rgdal.
Each AOI created by this function is a square with the length of each
side being the aoi.size
in number of pixels. For example, if
the desired AOI size was 300 meters on a side and the image
had
30 meter pixels the aoi.size
should be 100.
The minimum number of reference points within each AOI cannot be less
than 10. An error will display if min.points
is set less than that.
The seed option is available so identical AOIs can be made from
different images. See set.seed
for more information.
Returns an object of class
"nnDaoi"
, which is a list
containing the following components:
AOI.spatial |
a list of the AOIs. Each element in the list is an
object of class SpatialGridDataFrame |
AOI.data |
a list of the pixel values contained in each AOI. Each element in the list is a matrix. |
refPoint.index |
a list with the index of reference points contained in each AOI. Each element in the list is a vector. |
ref.coordinates |
a matrix of the reference point coordinates |
Plotting an "nnDaoi"
object will display the set of reference
points and outlines of each AOI.
Brian Walters walte137@msu.edu
McRoberts, R.E. (2009) Diagnostic tools for nearest neighbors techniques when used with satellite imagery, Remote Sensing of Environment. 113, 489–499.
Functions that use "nnDaoi"
objects: arealBias
, extrap
.
data(LuceVolume_subset) LuceVolImg <- GDAL.open(system.file("data/LuceSubset_Volume.tif", package = "nnDiag")) LuceTasscap <- GDAL.open(system.file("data/LuceSubset_Tcap.tif", package = "nnDiag")) LuceMask <- GDAL.open(system.file("data/LuceSubset_Mask.tif", package = "nnDiag")) coords <- as.matrix(LuceVolume_subset[,10:11]) vol.aoi <- aoiMaker(coords, 3, LuceVolImg, aoi.size = 20, min.points = 4, seed = 89) plot(vol.aoi) tcap.aoi <- aoiMaker(coords, 3, LuceTasscap, LuceMask, aoi.size = 20, min.points = 4, seed = 89) plot(tcap.aoi)