CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES

Marco A. Chavarria, Gerald Sommer

2008

Abstract

In this paper we present a new variant of ICP (iterative closest point) algorithm based on local feature correlation. Our approach combines global and local feature information to find better correspondence sets and to use them to compute the 3D pose of the object model even for the case of large displacements between model and image data. For such cases, we propose a 2D alignment in the image plane (rotation plus translation) before the feature extraction process. This has some advantages over the classical methods like better convergence and robustness. Furthermore, it avoids the need of a normal pre-alignment step in 3D. Our approach was tested on synthetical and real-world data to compare the convergence behavior and performance against other versions of the ICP algorithm combined with a classical pre-alignment approach.

References

  1. Araujo, H., Carceroni, R., and Brown, C. (1998). A fully projective formulation to improve the accuracy of Lowe's pose-estimation algorithm. Comput. Vis. Image Underst., 70(2):227-238.
  2. Besl, P. and McKay, N. (1992). A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2):239-256.
  3. Brujic, D. and Ristic, M. (1996). Analysis of free form surface registration. In International Conference of Image Processing. Lausanne, Switzerland, pages 393- 396.
  4. Chavarria, M. and Sommer, G. (2007). Structural icp algorithm for pose estimation. In 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, March 8-11, Barcelona, Spain, pages 341-346, Portugal. INSTICC.
  5. Felsberg, M. and Sommer, G. (2004). The monogenic scalespace: A unifying approach to phase-based image processing in scale-space. Journal of Mathematical Imaging and Vision, 21(1):5-26.
  6. Ladkos, A., Behimane, S., and Navab, N. (2007). A realtime tracking system combinig template-based and feature-based approaches. In 2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007, March 8-11, Barcelona, Spain, pages 325-332, Portugal. INSTICC.
  7. Lin, C.-S. and Hwang, C.-L. (1987). New forms of shape invariants from elliptic fourier descriptors. Pattern Recognition., 20(5):535-545.
  8. Lomonosov, E., Chetverikov, D., and Ekárt, A. (2006). Pre-registration of arbitrarily oriented 3d surfaces using a genetic algorithm. Pattern Recognition Letters, 27(11):1201-1208.
  9. Masuda, T., Sakaue, K., and Yokoya, N. (1996). Registration and integration of multiple range images for 3-d model construction. In ICPR 7896: Proceedings of the 1996 International Conference on Pattern Recognition (ICPR 7896) Volume I, page 879, Washington, DC, USA. IEEE Computer Society.
  10. Murino, V., Ronchetti, L., Castellani, U., and Fusiello, A. (2001). Reconstruction of complex environments by robust pre-aligned ICP. In Proc. Third Int. Conf. on 3-D Digital Imaging and Modeling, pages 187-194.
  11. Rosenhahn, B., Perwass, C., and Sommer, G. (2003). Pose estimation of free-form surface models. In Michaelis, B. and Krell, G., editors, 25. Symposium für Mustererkennung, DAGM 2003, Magdeburg, volume 2781 of LNCS, pages 574-581. Springer-Verlag, Berlin.
  12. Rosenhahn, B. and Sommer, G. (2005). Pose estimation in conformal geometric algebra, part II: Real-time pose estimation using extended feature concepts. Journal of Mathematical Imaging and Vision, 22:49-70.
  13. Rusinkiewicz, S. and Levoy, M. (2001). Efficient variants of the ICP algorithm. In Proceedings of the Third Intl. Conf. on 3D Digital Imaging and Modeling, pages 145-152, Quebec City, Canada.
  14. Shang, L., Jasiobedzki, P., and Greenspan, M. (2007). Model-based tracking by classification in a tiny discrete pose space. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6):976-989.
  15. Sharp, G., Lee, S., and Wehe, D. (2002). ICP registration using invariant features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(1):90- 102.
  16. Sommer, G., editor (2001). Geometric Computing with Clifford Algebras. Springer-Verlag, Heidelberg.
Download


Paper Citation


in Harvard Style

A. Chavarria M. and Sommer G. (2008). CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 528-534. DOI: 10.5220/0001079305280534


in Bibtex Style

@conference{visapp08,
author={Marco A. Chavarria and Gerald Sommer},
title={CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={528-534},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001079305280534},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - CORRELATION ICP ALGORITHM FOR POSE ESTIMATION BASED ON LOCAL AND GLOBAL FEATURES
SN - 978-989-8111-21-0
AU - A. Chavarria M.
AU - Sommer G.
PY - 2008
SP - 528
EP - 534
DO - 10.5220/0001079305280534