Advertisement

Machine Vision and Applications

, Volume 16, Issue 5, pp 267–272 | Cite as

Automatic model-based 3D object recognition by combining feature matching with tracking

  • Sungho KimEmail author
  • In So Kweon
Article

Abstract

We propose a vision-based robust automatic 3D object recognition, which provides object identification and 3D pose information by combining feature matching with tracking. For object identification, we propose a robust visual feature and a probabilistic voting scheme. An initial object pose is estimated using correlations between the model image and the 3D CAD model, which are predefined, and the homography, byproduct of the identification. In tracking, a Lie group formalism is used for robust and fast motion computation. Experimental results show that object recognition by the proposed method improves the recognition range considerably.

Keywords

Local Zernike moments Probabilistic voting Homography Automatic 3D pose initialization Real-time tracking 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Pattern Anal. Mach. Intell. 19(5), 872–877 (1998a)Google Scholar
  2. 2.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IEEE Trans. Pattern Anal. Mach. Intell. 60(2), 91–110 (2004)Google Scholar
  3. 3.
    Ohba, K., Ikeuchi, K.: Detectability, uniqueness, and reliability of eigen-windows for robust recognition of partially occluded objects. IEEE Pattern Anal. Mach. Intell. 19(9), 1043–1048 (1997)CrossRefGoogle Scholar
  4. 4.
    Kim, S., Kim, I., Kweon, I.: Probabilistic model-based object recognition using local Zernike moments. In: IAPR Workshop on Machine Vision Applications, pp. 334–337. Nara, Japan (2002)Google Scholar
  5. 5.
    Schmid, C., Mohr, R., Bauckhage, C.: Comparing and evaluating interest points. In: International Conference on Computer Vision, pp. 230–235. Bombay, India (1998b)Google Scholar
  6. 6.
    Abdallah, S., MEngSc, B.: Object recognition via invariance. PhD Thesis, The University of Sydney, pp. 14–29 (2000)Google Scholar
  7. 7.
    Teh, C., Chin, R.: On image analysis by the methods of moments. IEEE Trans. Pattern Anal. Mach. Intell. 10(4), 496–513 (1988)CrossRefzbMATHGoogle Scholar
  8. 8.
    Lindberg, T.: Scale-space theory: a basic tool for analyzing structures at different scales. J. Appl. Stat. 20(2), 224–270 (1994)Google Scholar
  9. 9.
    Kim, J., Gurdjos, P., Kweon, I.: Geometric and algebraic constraints of projective concentric circles and their applications to camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 27(4), 637–642 (2005)CrossRefPubMedGoogle Scholar
  10. 10.
    Drummond, T., Cipolla, R.: Real-time visual tracking of complex structures. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 932–946 (2002)CrossRefGoogle Scholar
  11. 11.
    Mikolajc, K., Schmid, C.: An affine invariant interest POINT detector. In: European Conference on Computer Vision (ECCV), pp. 128–142. Copenhagen, Denmark (2002)Google Scholar
  12. 12.
    Zhang, Z: Flexible camera calibration by viewing a plane from unknown orientations. In: International Conference on Computer Vision, pp. 666–673. Corfu, Greece (1999)Google Scholar

Copyright information

© Springer-Verlag 2005

Authors and Affiliations

  1. 1.Robotics & Computer Vision LaboratoryKorea Advanced Institute of Science and TechnologyDaejeonKorea

Personalised recommendations