auto_chg_detect: Perform change detection for two Landsat CDR surface...

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

Description

This image automates the change detection process using the Change Vector Analysis in Posterior Probability Space (CVAPS) algorithm. The threshold for change/no-change mapping is determined using Huang's algorithm (see threshold or can be specified manually. First the images should be classified using the auto_classify function (or any other classification approach that yields per-pixel probabilities of class membership).

Usage

auto_chg_detect(t1_classes, t1_probs, t2_probs, output_path, output_basename,
  ext = "tif", overwrite = FALSE, chg_threshold = NULL, notify = print)

Arguments

t1_classes	cover classes as output from auto_classify_image for time 1 image
t1_probs	per class probabilities as output from auto_classify_image for time 1 image
t2_probs	per class probabilities as output from auto_classify_image for time 2 image
output_path	the path to use for the output
output_basename	the base filename for output files from auto_chg_detect (without an extension)
ext	file extension to use when saving output rasters (determines output file format).
overwrite	whether to overwrite existing files (otherwise an error will be raised)
chg_threshold	the threshold to use determining change and no-change areas from the change magnitude image (see chg_mag. If NULL, then threshold will be used to dermine this threshold value automatically. A threshold in the range of .75-1 is recommended as a starting point.
notify	notifier to use (defaults to print function). See the notifyR package for one way of sending notifications from R. The notify function should accept a string as the only argument.

Value

nothing - used for the side effect of performing change detection

References

Chen, J., X. Chen, X. Cui, and J. Chen. 2011. Change vector analysis in posterior probability space: a new method for land cover change detection. IEEE Geoscience and Remote Sensing Letters 8:317-321.

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