The proliferation of unmanned aerial vehicles (UAVs) over the past decade has been driven by advancements in structure-from-motion (SfM), machine learning, and robotics. A crucial application in forestry is individual tree detection (ITD), essential for calculating forest attributes like stem volume, forest uniformity, and biomass estimation.
This whitepaper addresses the challenges users face in adopting UAVs and algorithms for specific projects by providing a detailed tutorial for performing ITD. It covers the use of low-cost UAV-derived imagery and UAV-based high-density LiDAR, utilizing open-source R packages to develop a canopy height model (CHM) and implement the local maxima (LM) algorithm for ITD.
Accuracy assessments are derived through manual visual interpretation and field-data validation. Targeted at beginners in remote sensing, this guide employs a simple methodology and uses study plots with relatively open canopies. Supplementary materials include R codes and sample plot data to facilitate practical application.
