Advertisement

Robust Three-Dimensional Registration of Range Images Using a New Genetic Algorithm

  • John Willian Branch
  • Flavio Prieto
  • Pierre Boulanger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4077)

Abstract

Given two approximately aligned range images of a real object, it is possible to carry out the registration of those images using numerous algorithms such as ICP. Registration is a fundamental stage in a 3D reconstruction process. Basically the task is to match two or more images taken in different times, from different sensors, or from different viewpoints. In this paper, we discuss a number of possible approaches to the registration problem and propose a new method based on the manual pre-alignment of the images followed by an automatic registration process using a novel genetic optimization algorithm. Results for real range data are presented. This procedure focuses, on the problem of obtaining the best correspondence between points through a robust search method between partially overlapped images.

Keywords

Registration range image ICP algorithm normal genetic algorithm 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Besl, P.: A method for Registration of 3-D Shapes. IEEE Trans. Pattern Analysis and Machine Intelligence 14 (1992)Google Scholar
  2. 2.
    Renner, G., Ekárt, A.: Genetic Algorithms. Computer-Aided Design, 709–726 (2003)Google Scholar
  3. 3.
    Brunnstrom, K.: Genetic Algorithms for Free-Form Surface Matching (1996)Google Scholar
  4. 4.
    Robertson, C.: Parallel Evolutionary Registration of Range Data. Computer Vision and Image Understanding, 87 (2002)Google Scholar
  5. 5.
    Silva, L.: Precision Range Image Registration Using a Robust Surface Interpretation Measure and Enhanced Genetic Algorithm. IEEE Trans. Pattern Analysis and Machine Intelligence 27, 762–776 (2005)CrossRefGoogle Scholar
  6. 6.
    Yamany, S.: New Genetic-Based Technique for Matching 3D Curves and Surfaces. Pattern Recognition 32, 1817–1820 (1999)CrossRefGoogle Scholar
  7. 7.
    Salomon, M.: Differential Evolution for Medical Image Registration. In: International Conference on Artificial Intelligence, pp. 201–207 (2001)Google Scholar
  8. 8.
    Chow, C.: Surface Registration Using a Dynamic Genetic Algorithm. Pattern Recognition 37, 105–117 (2004)zbMATHCrossRefGoogle Scholar
  9. 9.
    Horn, B.K.P.: Closed-Form Solution of Absolute Orientation. J. Opt. Soc. A 4, 629–642 (1987)CrossRefGoogle Scholar
  10. 10.
    Chen, Y.: Object modeling by registration of multiple range images. Image and Vision Computing 10 (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • John Willian Branch
    • 1
  • Flavio Prieto
    • 2
  • Pierre Boulanger
    • 3
  1. 1.Escuela de SistemasUniversidad Nacional de ColombiaSede Medellín
  2. 2.Departamento de Eléctrica, Electrónica y ComputaciónUniversidad Nacional de ColombiaSede Manizales
  3. 3.Department of Computing ScienceUniversity of AlbertaCanada

Personalised recommendations