Data Fusion by Uncertain Projective Geometry in 6DoF Visual SLAM

Daniele Marzorati, Matteo Matteucci, Davide Migliore, Domenico G. Sorrenti

Abstract

In this paper we face the issue of fusing 3D data from different sensors in a seamless way, using the unifying framework of uncertain projective geometry. Within this framework it is possible to describe, combine, and estimate various types of geometric elements (2D and 3D points, 2D and 3D lines, and 3D planes) taking their uncertainty into account. Because of the size of the data involved in this process, the integration process and thus the SLAM algorithm turns out to be very slow. For this reason, in this work, we propose the use of an R*-Tree data structure to speed up the whole process, managing in an efficent way both the estimated map and the 3D points clouds coming out from the stereo camera. The experimental section shows that the use of uncertain projective geometry and the R*-Tree data structure improves the mapping and the pose estimation.

References

  1. Durrant-Whyte, H.F.: Integration, coordination and control of multi-sensor robot systems. Kluwer Academic (1987)
  2. Lu, F., Milios, E.: Globally consistent range scan alignment for environment mapping. Autonomous Robots 4 (1997) 333-349
  3. Tardó s, J.D., Castellanos, J.A.: Mobile robot localization and map building: a multisensor fusion approach. Kluwer Academic (1999)
  4. Marzorati, D., Matteucci, M., D. Migliore, D.G.S.: Integration of 3d lines and points in 6dof visual slam by uncertain projective geometry. European Conference on Mobile Robotics (2007) 96 - 101
  5. Nü chter, A., Lingemann, K., Hertzberg, J.: 6D SLAM with Cached kd-tree Search. Number 06421 in Dagstuhl Seminar Proceedings. Internationales Begegnungs- und Forschungszentrum fü r Informatik (IBFI), Schloss Dagstuhl, Germany, Dagstuhl, Germany (2007)
  6. Nü chter, A., Lingemann, K., Hertzberg, J., Surmann, H.: 6d slam with approximate data association. 12th International Conference on Advanced Robotics, 2005. ICAR 7805. Proceedings (2005) 242-249
  7. Heuel, S.: Points, Lines and Planes and their Optimal Estimation. Number 2191 in LNCS. Springer (2001)
  8. Heuel, S.: Uncertain Projective Geometry: Statistical Reasoning for Polyhedral Object Reconstruction. Springer (2004)
  9. Konolige, K.: Small vision system. hardware and implementation. In: ISRR, Hayama, Japan (1997)
  10. Ayache, N., Lustman, F.: Trinocular stereo vision for robotics. IEEE Trans. on PAMI 12 (1991)
  11. Marzorati, D., Sorrenti, D.G., Matteucci, M.: Multi-criteria data association in 3d-6dof hierarchical slam with 3d segments. In: Proc. of ASER06 Conf. (2006)
  12. Marzorati, D., Sorrenti, D.G., Matteucci, M.: 3d-6dof hierarchical slam with trinocular vision. In: Proc. of ECMR. (2005)
  13. Beckmann, N., Kriegel, H.P., Schneider, R., Seeger, B.: The r*-tree: An efficient and robust access method for points and rectangles. SIGMOD Conference (1990) 322-331
  14. Lemaire, T., Lacroix, S., Sola, J.: A practical 3d bearing-only slam algorithm. In: Proc. of IROS. (2005)
  15. Davison, A.: Real-Time Simultaneous Localisation and Mapping with a Single Camera. In: Proc. of ICCV. (2003) 1403-1410
  16. Se, S., Lowe, D., Little, J.: Global localization using distinctive visual features. In: Proc. of IROS, Lausanne, Switzerland (2002)
Download


Paper Citation


in Harvard Style

Marzorati D., Matteucci M., Migliore D. and G. Sorrenti D. (2008). Data Fusion by Uncertain Projective Geometry in 6DoF Visual SLAM . In VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008) ISBN 978-989-8111-23-4, pages 3-12. DOI: 10.5220/0002341600030012


in Bibtex Style

@conference{visapp-roboperc08,
author={Daniele Marzorati and Matteo Matteucci and Davide Migliore and Domenico G. Sorrenti},
title={Data Fusion by Uncertain Projective Geometry in 6DoF Visual SLAM},
booktitle={VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008)},
year={2008},
pages={3-12},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002341600030012},
isbn={978-989-8111-23-4},
}


in EndNote Style

TY - CONF
JO - VISAPP-Robotic Perception - Volume 1: VISAPP-RoboPerc, (VISIGRAPP 2008)
TI - Data Fusion by Uncertain Projective Geometry in 6DoF Visual SLAM
SN - 978-989-8111-23-4
AU - Marzorati D.
AU - Matteucci M.
AU - Migliore D.
AU - G. Sorrenti D.
PY - 2008
SP - 3
EP - 12
DO - 10.5220/0002341600030012