ForestTools: Tools for analyzing remotely sensed forest data

Authors: Andrew Plowright
License: GPL 3

Build Status

The ForestTools R package offers functions to analyze remotely sensed forest data.

Detect and segment trees

Individual trees can be detected and delineated using a combination of the variable window filter (vwf) and marker-controlled segmentation (mcws) algorithms, both of which are applied to a rasterized canopy height model (CHM). CHMs are typically derived from aerial LiDAR or photogrammetric point clouds.

image info

Compute textural metrics

Grey-level co-occurrence matrices (GLCMs) and their associated statistics can be computed for individual trees using a single-band image and a segment raster (which can be produced using mcws). These metrics can be used to characterize and classify trees.

Summarize forest information

The height and count of treetops can be summarized within a grid or within user-defined geographical areas using sp_summarise.

image info


This library implements techniques developed in the following studies:


The following is a non-exhaustive list of research papers that use the ForestTools library. Several of these studies discuss topics such as algorithm parameterization, and may be informative for users of this library.