Ground plane identification using LIDAR in forested environments
2010 (English)In: 2010 ieee international conference on robotics and automation, IEEE Press, 2010, p. 3831-3836Conference paper, Published paper (Refereed)
Abstract [en]
To operate autonomously in forested environments, unmanned ground vehicles (UGVs) must be able to identify the load-bearing surface of the terrain (i.e. the ground). This paper presents a novel two-stage approach for identifying ground points from 3-D point clouds sensed using LIDAR. The first stage, a local height-based filter, discards most of the non-ground points. The second stage, based on a support vector machine (SVM) classifier, operates on a set of geometrically defined features to identify which of the remaining points belong to the ground. Experimental results from two forested environments demonstrate the effectiveness of this approach. ©2010 IEEE.
Place, publisher, year, edition, pages
IEEE Press, 2010. p. 3831-3836
Series
IEEE International Conference on Robotics and Automation. Proceedings, ISSN 1050-4729
Keywords [en]
Clouds, Digital elevation models, Filters, Land vehicles, Laser radar, Mars, Robotics and automation, Support vector machine classification, Support vector machines, USA Councils, computer vision, filtering theory, mobile robots, optical radar, pattern classification, remotely operated vehicles, support vector machines, 3D point cloud, LIDAR, forested environment, ground plane identification, load bearing surface, local height based filter, support vector machine classifier, unmanned ground vehicle
National Category
Robotics
Identifiers
URN: urn:nbn:se:hh:diva-20825DOI: 10.1109/ROBOT.2010.5509963Scopus ID: 2-s2.0-77955780198ISBN: 978-142445038-1 OAI: oai:DiVA.org:hh-20825DiVA, id: diva2:586708
Conference
2010 IEEE International Conference on Robotics and Automation, ICRA 2010, Anchorage, AK, 3-7 May, 2010
2013-01-122013-01-122018-03-22Bibliographically approved