Communications of the ACM
Algorithms to Enhance Forest Inventories
An Ecole Polytechnique Fdrale de Lausanne researcher developed algorithms capable of automatically determining inventory parameters of trees over large forests.
Credit: EPFL
Matthew Parkan, a researcher at Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, developed algorithms capable of automatically determining inventory parameters of trees over large forests.
These algorithms can be used to create a detailed map of an area in preparation for tree marking (prior to cutting), to closely monitor the development of individual trees, and to identify habitats most suited to certain animal species.
Parkan calibrated the algorithms using a reference dataset of more than 5,000 trees taken from a three-dimensional point cloud. For this, he created a digital forestry toolbox to facilitate the manual extraction of trees and the visual identification of tree species. This allowed Parkan to verify the algorithms could reliable detect the location and shape of trees, and to calibrate the classification models for nine tree species.
Said Parkan, "My aim was to develop methods and tools that can supplement on-the-ground inventories, rather than replace them."
From Ecole Polytechnique Fédérale de Lausanne
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA
No entries found