DYNAMIC REAL-TIME REDUCTION OF MAPPED FEATURES IN A 3D POINT CLOUD

Marko Reimer, Bernardo Wagner

2007

Abstract

This paper presents a method to reduce the data collected by a 3D laser range sensor. The complete point cloud consisting of several thousand points is hard to process on-line and in real-time on a robot. Similar to navigation tasks, the reduction of these points to a meaningful set is needed for further processes of object recognition. This method combines the data from a 3D laser sensor with an existing 2D map in order to reduce mapped feature points from the raw data. The main problem is the computational complexity of considering the different noise sources. The functionality of our approach is demonstrated by experiments for on-line reduction of the 3D data in indoor and outdoor environments.

Paper Citation

in Harvard Style

Reimer M. and Wagner B. (2007). DYNAMIC REAL-TIME REDUCTION OF MAPPED FEATURES IN A 3D POINT CLOUD . In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO, ISBN 978-972-8865-83-2, pages 363-369. DOI: 10.5220/0001638003630369

in Bibtex Style

@conference{icinco07,
author={Marko Reimer and Bernardo Wagner},
title={DYNAMIC REAL-TIME REDUCTION OF MAPPED FEATURES IN A 3D POINT CLOUD},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,},
year={2007},
pages={363-369},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001638003630369},
isbn={978-972-8865-83-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,
TI - DYNAMIC REAL-TIME REDUCTION OF MAPPED FEATURES IN A 3D POINT CLOUD
SN - 978-972-8865-83-2
AU - Reimer M.
AU - Wagner B.
PY - 2007
SP - 363
EP - 369
DO - 10.5220/0001638003630369