Automatic Three-Dimensional Point Cloud Processing for Forest Inventory - Robotics Institute Carnegie Mellon University

Automatic Three-Dimensional Point Cloud Processing for Forest Inventory

Jean-Francois Lalonde, Nicolas Vandapel, and Martial Hebert
Tech. Report, CMU-RI-TR-06-21, Robotics Institute, Carnegie Mellon University, July, 2006

Abstract

In this paper, we propose an approach that enables automatic, fast and accurate tree trunks segmentation from three-dimensional (3-D) laser data. Results have been demonstrated in real-time on-board a ground mobile robot. In addition, we propose an approach to estimate tree diameter at breast height (dbh) that was tested off-line on a variety of ground laser scanner data. Results are also presented for detection of tree trunks in aerial laser data. The underlying techniques using in all cases rely on 3-D geometry analysis of point clouds and geometric primitives fitting.

BibTeX

@techreport{Lalonde-2006-9530,
author = {Jean-Francois Lalonde and Nicolas Vandapel and Martial Hebert},
title = {Automatic Three-Dimensional Point Cloud Processing for Forest Inventory},
year = {2006},
month = {July},
institute = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-06-21},
keywords = {forest inventory, 3d point cloud, ladar, laser},
}