Advertisement

3-D reconstruction of multipart self-occluding objects

  • Nebojsa Jojic
  • Jin Gu
  • Helen C. Shen
  • Thomas Huang
Session S3A: Onject Recognition and Modeling
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)

Abstract

In this paper we present a method for reconstruction of multipart objects from several arbitrary views using deformable superquadrics as the models of the object's parts. Two visual cues are used: occluding contours and stereo (possibly aided by projected patterns). The object can be relatively complex and can exhibit numerous self occlusions from some or all views. Our preliminary experiments on a human body and a tailor's mannequin show that the reconstruction is more complete than in purely stereo or structured light based methods and more precise than the reconstruction from occluding contours only.

Keywords

Feature Point Model Point Stereo Match Contour Point Contour Segment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    H. G. Barrow, J. M. Tenenbaum, R. C. Bollers, and H. C. Wolf. Parametric correspondence and chamfer matching: Two new techniques for image matching. Vision-7, pages 659–63, 1979.Google Scholar
  2. 2.
    N. Jojic and T. S. Huang. On analysis of cloth drape range data. In these proceedings (ACCV '98).Google Scholar
  3. 3.
    I. Kakadiaris and D. Metaxas. Model-based estimation of 3d human motion with occlusion based on active multi-viewpoint selection. In Proceedings 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 81–7, 1996.Google Scholar
  4. 4.
    I. A. Kakadiaris. Motion-Based Part Segmentation, Shape and Motion Estimation of Complex Multi-Part Objects: Application To Human Body Tracking. PhD thesis, University of Pennsylvania, Philadelphia, PA, 1996.Google Scholar
  5. 5.
    D. Metaxas and D. Terzopoulos. Shape and nonrigid motion estimation through physics-based synthesis. IEEE Transaction on Pattern Analysis and Machine Intelligence, 15(6):580–91, 1993.Google Scholar
  6. 6.
    D. Terzopoulos and D. Metaxas. Dynamic 3d models with local and global deformations: Deformable superquadrics. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(7):703–14, 1991.Google Scholar
  7. 7.
    Y. F. Wang and J. K. Aggarwal. Integration of active and passive sensing techniques for representing three-dimensional objects. IEEE Transactions on Robotics and Automation, 5(4):460–71, 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Nebojsa Jojic
    • 1
  • Jin Gu
    • 2
  • Helen C. Shen
    • 2
  • Thomas Huang
    • 1
  1. 1.Beckman InstituteUniversity of Illinois at Urbana-ChampaignUrbanaUSA
  2. 2.Department of Computer ScienceHong Kong University of Science and TechnologyHong Kong

Personalised recommendations