hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Terrain classification and identification of tree stems using ground-based LiDAR
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA.
Show others and affiliations
2012 (English)In: Journal of Field Robotics, ISSN 1556-4967, Vol. 29, no 6, p. 891-910Article in journal (Refereed) Published
Abstract [en]

To operate autonomously in forested terrain, unmanned ground vehicles must be able to identify the load-bearing surface of the terrain(i.e., the ground) and obstacles in the environment. To travel long distances, they must be able to track their position even when the forest canopy obstructs GPS signals, e.g., by tracking progress relative to tree stems. This paper presents a novel, robust approach for modeling the ground plane and tree stems in forests from a single viewpoint using a lightweight LiDAR scanner. Ground plane identification is implemented using a two-stage approach. The first stage, a local height-based filter, discards most nonground points. The second stage,based on a support vector machine classifier, identifies which of the remaining points belong to the ground. Main tree stems are modeled as cylinders or cones to estimate the diameter 130 cm above the ground plane. To fit these models, candidate main stem data are selected by finding points approximately 130 cm above the ground. These points are clustered into separate point clouds for each stem. Cylinders and cones are fit to each point cloud, and heuristic filters identify which fits correspond to tree stems. Experimental results from five forested environments demonstrate the effectiveness of this approach. For ground plane estimation, the overall classification accuracy was 86.28% with a mean error for the ground height of approximately 4.7 cm. For stem estimation, up to 50% of the main stems were accurately modeled using cones, with a root mean square diameter error of 13.2 cm.© 2012 Wiley Periodicals, Inc. Copyright © 2012 Wiley Periodicals, Inc.

Place, publisher, year, edition, pages
Hoboken: John Wiley & Sons, 2012. Vol. 29, no 6, p. 891-910
National Category
Robotics
Identifiers
URN: urn:nbn:se:hh:diva-20612DOI: 10.1002/rob.21422ISI: 000309457200004Scopus ID: 2-s2.0-84867101105OAI: oai:DiVA.org:hh-20612DiVA, id: diva2:585331
Available from: 2013-01-09 Created: 2013-01-09 Last updated: 2018-03-22Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Iagnemma, Karl

Search in DiVA

By author/editor
Iagnemma, Karl
Robotics

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 72 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf