TOWARD LARGE SCALE MODEL CONSTRUCTION FOR VISION-BASED GLOBAL LOCALISATION

P. Lothe, S. Bourgeois, F. Dekeyser, E. Royer, M. Dhome

Abstract

Monocular SLAM reconstruction algorithm advancements enable their integration in various applications: trajectometry, 3D model reconstruction, etc. However proposed methods still have drift limitations when applied to large-scale sequences. In this paper, we propose a post-processing algorithm which exploits a CAD model to correct SLAM reconstructions. The presented method is based on a specific deformable transformations model and then on an adapted non-rigid ICP between the reconstructed 3D point cloud and the known CAD model. Experimental results on both synthetic and real sequences point out that the 3D scene geometry regains its consistency and that the camera trajectory is improved: mean distance between the reconstructed cameras and the ground truth is less than 1 meter on several hundreds of meters.

References

  1. Castellani, U., Gay-Bellile, V., and Bartoli, A. (2007). Joint reconstruction and registration of a deformable planar surface observed by a 3d sensor. In 3DIM, pages 201- 208.
  2. Davison, A., Reid, I., Molton, N., and Stasse, O. (2007). MonoSLAM: Real-time single camera SLAM. PAMI, 26(6):1052-1067.
  3. Fitzgibbon, A. (2001). Robust registration of 2d and 3d point sets. In BMVC, pages 411-420.
  4. Huber, P. (1981). Robust Statistics. Wiley, New-York.
  5. Levenberg, K. (1944). A method for the solution of certain non-linear problems in least squares. Quart. Appl. Math., 2:164-168.
  6. Levin, A. and Szeliski, R. (2004). Visual odometry and map correlation. In CVPR, pages 611-618.
  7. Lowe, D. G. (1987). Three-Dimensional Object Recognition from Single Two-Dimensional Images. Artificial Intelligence, 31(3):355-395.
  8. Mouragnon, E., Dekeyser, F., Sayd, P., Lhuillier, M., and Dhome, M. (2006). Real time localization and 3d reconstruction. In CVPR, pages 363-370.
  9. Nister, D., Naroditsky, O., and Bergen, J. (2004). Visual odometry. In CVPR, pages 652-659.
  10. Royer, E., Lhuillier, M., Dhome, M., and Chateau, T. (2005). Localization in urban environments: Monocular vision compared to a differential gps sensor. In CVPR, pages 114-121.
  11. Rusinkiewicz, S. and Levoy, M. (2001). Efficient variants of the ICP algorithm. In 3DIM, pages 145-152.
  12. Sourimant, G., Morin, L., and Bouatouch, K. (2007). Gps, gis and video fusion for urban modeling. In CGI.
  13. Zhao, W., Nister, D., and Hsu, S. (2005). Alignment of continuous video onto 3d point clouds. PAMI, 27(8):1305-1318.
Download


Paper Citation


in Harvard Style

Lothe P., Bourgeois S., Dekeyser F., Royer E. and Dhome M. (2009). TOWARD LARGE SCALE MODEL CONSTRUCTION FOR VISION-BASED GLOBAL LOCALISATION . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 429-434. DOI: 10.5220/0001654204290434


in Bibtex Style

@conference{visapp09,
author={P. Lothe and S. Bourgeois and F. Dekeyser and E. Royer and M. Dhome},
title={TOWARD LARGE SCALE MODEL CONSTRUCTION FOR VISION-BASED GLOBAL LOCALISATION},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={429-434},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001654204290434},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - TOWARD LARGE SCALE MODEL CONSTRUCTION FOR VISION-BASED GLOBAL LOCALISATION
SN - 978-989-8111-69-2
AU - Lothe P.
AU - Bourgeois S.
AU - Dekeyser F.
AU - Royer E.
AU - Dhome M.
PY - 2009
SP - 429
EP - 434
DO - 10.5220/0001654204290434